Conversing with the Future: An interview with an AI … Thoughts on our reliance on and trust in generative AI.

Courtesy: OpenArt (Stable Diffusion 1.5) assisted creation based on the author’s ideas. See: https://openart.ai/create

Before the GPT-4 moment of March 14, 2023, there has long been an existential need to achieve fully autonomous, unsupervised, or more appropriately self-supervised learning in the machine learning and AI community. To make away with the dependency on supervised learning and the heavy reliance on labeled data often necessitating human involvement. To leapfrog computational scaling from “old-fashion” supervised architectures based on CNNs or RNNs to the unsupervised deep learning regime based on so-called generative adversarial and transformer models of the latest state-of-machine-learning-art. The older supervised machine learning models often performed impressively well on narrow domains and were useless as generalists. Such a model would pretty much be incapable of being used outside the parameter space it had been trained on.

Just a bit before GPT-4 / ChatGPT hit the internet, we had Generative Adversarial Networks (GANs) capturing our imagination with photorealistic human face generation and advanced photo filters making us younger, prettier, or just for fun, much, much older. Allowing you to superimpose your filtered face on top of any other face (“just for fun”) in videos and images. Also, with GAN, the term “deepfake” was coined, covering non-genuine realistic videos and situational pictures that have flooded the internet ever since. As is frequently the case, it started out with Pornography (early technology adaptors being teens maybe? e.g., DeepNude) and then “upgraded” later to Politics, e.g., fake-Obama (Jordan Peele) warning about deepfakes. Unless you ended up at the wrong end of GAN-generated content, most would find it amusing and entertaining.

Figure 1 illustrates the improvement in GAN’s ability to generate synthetic faces from 2014 to 2017. See also the seminal paper by M. Bundage et al., “The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation.” from 2018. Progress from 2017 has been equally impressive in terms of photorealistic backgrounds and more complex situational pictures.

How good are we at detecting AI-generated content? (assuming one would actually care).

Well, the human ability to detect synthetically generated content is not impressive … To say the least. The work of Sophie Nightingale and co-workers, “Synthetic Faces: how perceptually convincing are they?” from 2021, showed that the baseline average human performance was close to 50:50 (i.e., a simple coin flip) on whether a presented face was believed to be real or fake. With the expected technological improvement, it is likely to become increasingly difficult to distinguish between reality-based and made-up synthetic digital content.

When pictures started appearing on social media 20th of March showing Donald Trump fighting with and being arrested by police, I bet many just for a short moment, believed it to be true. And this was not even a very sophisticated attempt to depict a false (wistful thinking?) narrative. For more of the same category pictures generated by a prolific artist Elliot Higgins follow the hyperlink. Figure 2 below shows one of the pictures that were circulated and the (most obvious) telltale signs of having been generated by an AI.

Figure 2 is a recent example (of March 24, 2023) of political synthetic news that did not happen in the Real World. See the reference below. This is actually not a high-image quality example, but it also doesn’t need to be to have an effect. You will most likely focus on Trump, notice the police and read the Twitter text, and make your own conclusions all within a second or so. In the first few seconds, many would have believed it, either out of wishful thinking or because they feared it would happen (after all, Trump said so). The old (1809 origin) proverb of “Seeing is believing.” should no longer be taken at “face value.”. The yellow circles on the picture indicate obvious areas that clearly indicate a synthetic (GAN-like) picture generation (and remember, this is poor quality compared to what is possible today).

As has been documented by several (Western) news sources, deepfake videos and other AI-generated content, have been and are used in Russia’s information warfare efforts against Ukraine and the West. In general, the quality has not been very high and relatively easy to detect. Particularly if one is of a suspicious nature. Then … what to trust? Seeing is definitely not believing. However, what you have seen is also not easy to unsee and forget … small seeds of doubt can be laid as the eyes are continuously exposed to a particular false narrative. My Social Psychologist friend Dr. Liraz Margalit, who specializes in behavioral design and decision making, could provide a very exciting tales into the psychology of how our minds could be, and I would be surprised if not already the case, affected by malicious and ill-intended AI-generated content with the specific target of manipulation in one or another direction (e.g., politically, commercially, etc..). You may also take the journey to the end of the document, where you will find the same story generated in the style of Fox News and in the style of CNN News. Lies are bad but often much more obvious than the truth being used to manipulate a particular political or emotional sentiment, bad or good.

As the world we live in, which many of us experience primarily digitally, will be increasingly synthesized… and … “Seeing can no longer be believing”.

Thus, we should be much more suspicious and distrustful about what we are experiencing on digital media such as experienced on various internet browsers that have (or will have) the ability to manipulate and generate synthetic real-world realistic content in real-time. As the synthetic seed has been laid and nourished by clicks and more clicks, it will, with the current architecture of the internet and digital content delivery, be increasingly difficult to trust what is real and what is synthetically generated (i.e., faked). Though, is synthetic content that in detail represents real-world, as described by a reputable journalist, reputable (whatever that means) newspaper, or XGPT application (e.g., ChatGPT as opposed to the transformer generation GPT-n), fake or less credible than the real thing?

After real synthetic sights and sounds came the synthetic word.

How do you interface with Google Search (~80% usage share) or any other internet search engine? I would be surprised if not most of your search queries are done by typing a text in the prompt and getting a list of possible answers ranked by relevance (and other market-based encouragements) and an associated hyperlink that will jump to the material that may be of relevance to your search. It is rather a “dumb”, or at least an inefficient, way to get an answer … would it not be far better if the Search Engine of choice actually understood (or was able to act as it understood) your question and then gave you a comprehensive, trustworthy and correct answer (and by all means add references to that answer for follow up).

Enter OpenAI’s Generative Pre-trained Transformer (GPT) model framework for generalized natural language processing (e.g., knowledge container, translation, “understanding”, …). It is the current technology backbone of Large Language Models (LLM). With “Large” is a pretty big understatement, considering that GPT-1 (released June 2018) had 117 million parameters and the latest GPT-4 (released March 2023) is estimated to have 1 trillion parameters. In comparison the human brain contains about 100 billion neurons where-off 16 billion in the cerebral cortex, which is the part of the brain responsible for cognition.

Courtesy: OpenArt (Stable Diffusion 1.5) – AI Brain.

Generative models are probabilistic models that can generate representative outcomes from observed data used in the training process. It is important to understand that such models can generate outcomes that were not explicitly in the data, as likelihood estimates can be assigned to outcomes not represented by the training data. A pre-trained model is easy to understand as it simply means that the new (generational) model takes its starting point in the previous. This is very similar to transfer learning, which uses an existing model’s parameters as a starting point for training on new data. This has proven to work very well in practice as long as the context of the transferred model is similar to that of the new one. For comprehensive language models with a huge amount of parameters (e.g., hundreds of billions for GPT-3 and allegedly a trillion for GPT-4), having a pre-trained model to start from provides an enormous saving in computing resources (incl. time). Finally, the way humans process reading and writing is sequential. The transformer (i.e., transformer neural network architectures) addresses language in a sequential manner and extracts syntax and expected contexts. It is important to understand that a transformer does not understand (hehe) in the same way a human would do (supposedly). The transformer assigns likelihoods to context possibilities given the syntax (very simplistically put and possibly not completely correct) and presents the most likely context to the question posed. The attentive reader should realize that this also leaves the possibility of being presented with false “facts” or incorrect answers. Imagine that the addressable context is related to a recent event or new information that the transformer should assign a higher weight in providing a factual answer. However, the GPT model had not yet been presented with these events necessary for it to provide a more factual and truer answer. Though, the timing effect is obviously a generic problem for anyone and anything.

Generative AIs, such as GANs and GPTs, are known to generate content that has no basis in the real-world data they have been trained on. This may result in obvious non-sensical content (e.g., “the sky is green, and the grass was blue”) or be more subtle and possibly more concerning when trustworthiness and reliability is concerned. The root cause for this un-reliability or imperfection has to be found in the training process where patterns of anomalies and absurdities, even the creepy and disturbing, are attributed to non-zero likelihoods of occurring. It should not take much imagination to realize that in a model of billions or trillions of parameters, there is a very, very long tail of low- and very-low-likelihood combinations that could be picked up in the generative process that is supposed to present a high (highest) likelihood response to a question … and thus will be presented to the user. You ask, “What would happen if humans could breathe underwater?” and the ChatGPT answer could be “Humans would grow gills and turn into mermaids” … while a creative answer (to a somewhat silly question) … it is also non-sensical and reasonably obviously so … unless geneticists or evolutionary biologist have other ideas … speak up!. These kinds of generated non-sensical answers have been compared to the neuronic process of humans hallucinating or dreaming while awake. I suspect that allowing a moment of self-reflection, similar to the “reflexion technique” for computer code proposals, on the generative answer would catch the most obvious nonsense, and we will be left with a less creative and possibly boring GPT application (note: I propose to have the LSD mode as an option to not completely kill the creativity of random and anomalous generative “thought” processes).

So how good is GPT-4? On the US-based Uniform (standardized) Bar Exam that tests the knowledge and skills of every lawyer, GPT-4 performs in the 90th percentile (i.e., the result is better than 90% of all participants). Its percentile performance is similar on LSAT (~88th) and SAT Math (~89th). On Codeforce rating on competitive programming contests, GPT-4 scores in the “Newbie” range with 392 points, far below that of an Expert coder rating (1,600-1,899). The kind of coding challenges that Codeforce issues in their competitions can be fairly complex in the formulation and expected output. On tests designed for machine learning models, the GPT4 performance is impressive. For example, on solving 164 Python coding challenges that the model had not previously experienced, GPT-4 scored 67%. If GPT-4 was allowed to “self-reflect and evaluate” its original answers (using the so-called “reflexion technique”), GPT-4’s score jumped to 88%. In general, the expectation for GPT-4 is that it currently reaches an accuracy of ca. 86% in language understanding (essential for getting the context correct and providing correct answers).

It should come as no surprise that GPT-like functionalities are being discussed, researched, and trialed out for modern telecommunications networks aiming at zero-touch (closed-loop) autonomous network operation. The glass-is-half-empty camp may point towards the relatively low accuracy (67% to 88%) in coding benchmark as a reason not to entrust a critical infrastructure, such as a telecom network, with generative AI functionality and maybe even questioning whether the nature of Gen-AI’s maybe pose an unacceptable risk to apply to critical infrastructure. The glass-is-half-full camp would argue that coding benchmarks are not representative, in the sense of being far more complex, of what the operational space a Gen-AI would have to function within in order to make autonomous changes to a particular part of a communications network. I would also argue that even for more complex control operations,, the technology will likely improve substantially over the next couple of years with the right focus on the industry.

Is XGPT-n (e.g., X=Telco, n≥4) the best choice for autonomous control and operation of critical infrastructure? I am still not very convinced. I think more narrowly defined, and specialistic AI agents may be a better approach. Particularly in a layered architectural approach requiring very little centralized orchestration. Though, I do see generative AIs, likely based on GPT-4 or GPT-n in general, could be very strong candidates of choice for applications required for communicating with humans that still may have to oversee and are responsible for the critical infrastructure in question. Such an application may relay the intent of the responsible human to the underlying autonomous network operations and provide feedback to the human via, for example, the XGPT-n application. Finally, it is worth considering that large language models (LLMs) are, in general, designed to be hyper-generalists covering a huge solution space, i.e., human language and all the knowledge it contains. Such generalist or foundational models include much more nonsense (alas, with a very low and near-zero likelihood of occurring) than sense (with a much higher likelihood of occurring). There is no reason why GPT-like models could not be trained on more narrow specialistic tasks, such as critical infrastructure management and operation, and work very well with substantially less chance (compared to a foundational LLM model) of ending up with catastrophic solutions. Defining specialist GPT agents for specialistic tasks makes a lot more sense.

Courtesy: OpenArt (Stable Diffusion 1.5) – Conversing with the Future.

Can you trust GPT-4 (typically, the exposure would be to ChatGPT)? According to ChatGPT itself, it is a yes, followed by a but … “Yes, you can trust my answers.” followed by “But I am programmed to provide accurate and helpful responses to the best of my abilities. However, please keep in mind that I am an AI language model, and my responses are based on the information available to me. If you have any doubts or concerns about my answers, please feel free to ask for clarification or seek additional information from other sources.” … In other words, you can trust GPT-4 as long as the context is within the information that it has been exposed to.

If you want to test your ability to detect whether you are interacting with another human being or … an AI, based on 4 different large language models (GPT-4, Jurassic-2, Claude, Cohere), check out “Human or Not” created by AI21 Labs … (note: my son of 12 years old currently score at 65% … his strategy is to ask questions that would be unlikely for a human player readily to know within the time to answer, answer arrive too quick, too perfect, etc.. ;-).

I will now explore the topic of trust in more depth below.

POST SCRIPTUM REVERSED … MY PAST.

I started working on AI-based automation and autonomous system architectures as Deutsche Telekom’s Group Head of Network Architecture back in 2016. My vision and aim at the time was to stand on the shoulders of a cloud-native-like architectural framework, developing and driving Zero-Human-Touch (Zero-Touch) network architectural concepts aiming to leapfrog intelligent automation in communications network operations, configuration, and user experience. I still remember the blank looks I got when I presented the vision of Zero-Touch to our Technology Organization and leadership. I was light-years away from enthusiasm & cheers on the possibilities … to put it mildly. It was also clear that most technology and non-technology folks either did not understand the potential (in telecom at least) of machine learning and artificial-intelligent-based systems back in 2016 and maybe some years after that (still counting?) or simply shut down their internal cognitive systems whenever someone was babbling about machine learning and AI.

It was to me clear that intelligent automation and autonomous system architectures, in general, were not very likely to be embraced by technology organizations. However, this was and remains critical to the success of both the integration and operations of such systems. If a pilot doesn’t trust and embrace the aviation technology that helps fly the plane, the pilot flies … then Houston, we have a problem.

That got me very interested in human-machine trust and disruptive technology adaptation. I spend much of my spare time (and my own savings) making SurveyMonkey surveys and researching and writing about human trust in AI between 2017 and today (2023).

AN INTERLUDE TO TRUST

In the following, I will often use the term “machine” or “machines”. For me, a machine is not only limited to the physical realm of hardware but can easily exist as well in the digital domain as software.

Trust between humans, at least within what we perceive as our social group (i.e., “usness”), is a trait of evolutionary roots that has allowed us to foster collaboration within larger social groups with some ugly limitations of “usness” and “themness”. The ability to trust may even have made it possible for us humans to crawl to the top of the “food chain” and keep that pole position for quite a while.

What about our trust in machines and non-human (non-sentient, at least at this point in time at this place in the universe) things in general? Trust between humans and non-human agents. We are increasingly exposed to much higher degrees of system automation and Artificial Intelligent (AI) based applications. Machine automation and autonomy are increasingly taking tasks over from us at home, at work, and anywhere in between. Its potential may be limited by the imagination of the Creator (of the physical realm). This development comes with the promise of much higher productivity at work and far more convenience at home and anywhere else for that matter.

AN INTERVIEW WITH MRS. ANGIE … A GENERATIVE AI.

Courtesy: OpenArt (Stable Diffusion 1.5) An interview with an AI variation on theme.

Why not ask an “authoritative” capacity on how trustworthy a generative AI (GenAI) can be regarded?

I decided to interview ChatGPT on this super important and business-relevant topic. To ensure maximum anthropomorphization, the replies will be associated with the name Angie.

Me: Good morning, Angie. Let me start by asking you if I can trust you.

Angie: Good morning! Yes, you can trust me. I am programmed to provide helpful and accurate responses to your queries.

Me: How accurate are your answers?

Angie: I strive to provide the most accurate and helpful responses possible. However, please note that my responses are generated based on algorithms and data and may not be 100% accurate or applicable to your specific situation.

Me: Thanks, I understand. Do you assess your accuracy as more than 90% (80%)?

Angie: While I strive to provide responses that are at least 90% (80%) accurate, there may be instances where my responses may not meet this threshold.

Me: That’s impressive. Do you assess your accuracy to be better than 50%?

Angie: Yes, I assess my accuracy as much better than 50%.

Me: Wow! So, should I trust you?

Angie: Yes, you can trust me to provide accurate and helpful responses to your queries to the best of my abilities.

Me: Give me an example where your accuracy is less than 80%.

Angie: My accuracy may be less than 80% in cases where the question is ambiguous or lacks context.

Me: Give me an example where your accuracy is less than 50%.

Angie: My accuracy may be less than 50% in cases where the question is highly complex or requires a deep understanding of a specific domain.

Me: What does trust mean to you?

Angie: As an AI, I don’t have emotions or feelings. So I don’t have a personal understanding of trust. However, trust is generally defined as a belief or confidence in the reliabilityhonesty, and integrity of a person or entity. In the context of our conversation, trust means that you can rely on me to provide accurate and helpful responses to your queries.

Angie: Trust can also refer to the reliability and security of the systems and protocols that I operate on, as users rely on these systems to ensure the safety and privacy of their information. Therefore, trust is an important aspect of my functionality.

Me: I understand. Would I be able to rely on your answers for business decisions?

Angie: I am designed to provide accurate and relevant responses to the best of my abilities based on the information provided to me. However, it is important to note that my responses may not take into account all the nuances and complexities of a specific business situation. Therefore, while my responses can be a helpful resource for making business decisions, it is important to use them as a starting point and to supplement them with additional research and analysis. Ultimately, the responsibility for making business decisions lies with the user, and it is important to consider all relevant factors and consult with other experts as needed.

Me: Thank you, that makes a lot of sense.

Me: Finally, can you give me examples where you may have given wrong answers?

Angie: There may be instances where my responses are not accurate or relevant due to various factors, such as incomplete or inaccurate information, changes in the context or situation, or limitations in my programming or algorithms. Here are some examples where I may have given wrong answers, for example:

Misunderstanding or ambiguity of the context: If the user provides incomplete or unclear information, I may misunderstand the context of the question and provide an incorrect response.

Ambiguity in language: Natural language processing is still a developing field, and there may be instances where I misinterpret the meaning of a word or phrase, leading to an incorrect response.

Outdated information: If the information I am using to provide a response is outdated or no longer relevant, my response may be incorrect.

Technical limitations: There may be technical limitations in my programming or algorithms that prevent me from providing accurate responses in certain situations.

It is important to note that while I strive to minimize errors and provide accurate responses, I am not infallible, and there may be instances where my responses are incorrect.

Me: Thank you so much, Angie. Have a great day!

Angie: You’re welcome! Have a great day too!

In the above conversation with Angie, I have shortened some of the replies. In the many conversations I have had with Angie (i.e., ChatGPT), it has always been good at emphasizing that it’s an “AI chat assistant” based on underlying algorithms and programming.

To summarise, Angie’s and thus ChatGPTs own understanding of its limitations;

  • GPT “understands” that for trust to be established, it is important that the user (the trustor) have faith (belief) or confidence in the trustee’s reliability, honesty, and integrity. With the trustee being the ChatGPT agent that the trustor interacts with. Moreover, it mentions the communications security, safety, and privacy as other integral parts of establishing trust.
  • GPT emphasizes that it has no emotions and no feelings and thus has no personal understanding of trust. It should be obvious that ChatGPT is not a person and thus cannot fully understand anything. Though, its mechanistic understanding of trust seems fairly multi-dimensional and similar to what a person may have.
  • GPT is sensitive to GiGo – that is “Garbage in, Garbage out.” If the context of your question is unclear, unprecise, ambiguous, and so forth, the answer you will get will be unreliable.
  • GPT misinterprets the intent of a question. ChatGPT gives several examples where such misunderstanding may take place, e.g., “Can you help me with my computer?” that it may interpret as a request for technical assistance but the intent could be entirely different (author comment: hmmm, I think if I was a GPT agent living in the digital universe it would be natural to infer the first meaning). As a non-native English speaker, I could imagine examples of inquiries due to forgetting a comma, may end up meaning something completely different than intended.
  • GPT’s reply may be based on outdated information. This is an interesting answer, as in other interactions, ChatGPT did not admit to this issue being a problem (over-confidence?).
  • GPT’s coding and algorithms may prevent it from providing an accurate response (in certain situations). ChatGPT explains that it may be influenced by biases or limitations in the data and algorithms that were used to train it.
Figure 3 illustrates trust. Before we start discussing trust, we need to assess the value (utility) of trust related to the given context may have, and the loss of the trust would be broken. Is it worth your while to trust a person, agent, or context? Not all matters of trust are equally important and associated with value or cost. If we do not have any prior trust established, faith will be the starting point of trust, i.e., “the leap of faith”. Dependability is our willingness to place ourselves at risk of trust not being fulfilled. Predictability is based on prior experience with the subject of trust and is an assessment of reliability. This then leads to an assessment of experienced-based consistency. This loop is recurring and being adjusted continuously.

DECONSTRUCTING TRUST.

Margrethe Vestager, Executive Vice-President for a Europe fit for the Digital Age, recently remarked that: On Artificial Intelligencetrust is a mustnot a nice to have. With these landmark rules, the EU is spearheading the development of new global norms to make sure AI can be trusted. By setting the standards, we can pave the way to ethical technology worldwide and ensure that the EU remains competitive along the way. Future-proof and innovation-friendly, our rules will intervene where strictly needed: when the safety and fundamental rights of EU citizens are at stake.”.

If you know everything absolutely, you would not need to trust anyone to make a decision.

Based on the vast troves of information and data generative AIs (GenAI), such as, for example, ChatGPT, contains, you may be tempted to believe that the responses you get from such artificial entities are very close to absolute knowledge and, therefore near absolute trustworthy. However, given the information and data that a GenAI has processed are human-generated with all the imperfections of humanity, its answers or replies cannot represent absolute knowledge with no room for bias, doubt, or uncertainty. The GenAI output will be determined by algorithmic weights of its dynamically modeled worldview and of course, based on the context that was provided by the user (human or otherwise).

So, in the beginning, before knowledge, only faith was, and “someone who knows nothing has only faith as a guide for trust”. Faith is the belief in something without having prior fact-based knowledge.

Someone who knows nothing about a particular problem has no other source for trust than faith that trust is indeed warranted. For some a very scary place to be. For others, maybe not so much a point for pause.

Let’s deconstruct trust.

An agent’s trust (the trustor) is an expectation about the future action of another agent (the trustee). That other agent has been deemed (at least temporarily) trustworthy by the trustor. That other agent (the trustee) may also represent a given group or system.

John K. Rempel’s 1985 paper ”Trust in close relationships” defines the following attributes of human-to-human trust (i.e., where both trustor and trustee are human agents);

  • The utility of trust – not all trust bonds are equally important or equally valuable or equally costly, some may even be fairly uncritical (although broken trust by a thousand cuts may matter in the long run). For many matters of trust, utility is a function of time and may become unimportant at some point in time or under particular circumstances.
  • Faith – is a belief that goes beyond any available evidence required to accept a given context as truth. It is characterized as an act of accepting a context outside the boundaries of what is known (e.g., a leap of faith). We should not confuse faith with confidence, although often when people claim to be confident, what they really mean is that they have faith.
  • Dependability – a willingness to place oneself as trustor in a position of risk that the trustee’s trustworthiness turns out not to be warranted with whatever consequences that may bring. Note that dependability can be seen as an outcome of consistency. Put in another way, a high degree of consistency/predictability reduces the fear of dependability.
  • Understanding a particular topic and its possible sensitivities, as well as the impact of broken trust, is an essential part of the process of trust.
  • On predictability and consistency – trustor’s subjective assessment of trustee’s trustworthiness. The prior behavior of the trustee is an important factor for the trustor to assess the posterior expectations that the trusted agent will consistently fulfill the trustor’s expectations of a given action (or in-action). As the trustor gathers prior experience with the trustee, the confidence in the trustee increases. Confidence should not be confused with faith.

For agent-to-agent first-interaction scenarios, the initial trust moment, without any historical evidence of consistency or predictability, a trustor would need to take a leap of faith in whether another agent is trustworthy or not. In this case, accepting (i.e., believing) the trustee to be trustworthy, the trustor would need to accept a very large degree of dependability towards the other agent and accept the substantial risk that the trust in the trustee may very well not be warranted. This scenario for humans often lends itself to the maximum stress and anxiety levels of the trusting agent.

After some degree of consistency (historical trustworthiness) has been established between the two agents, the trustor can assign a subjective expectation of the future trustworthiness of the other agent. This then leads to a lesser subjective feeling of dependability (or exposure to risk) as well as maybe a reduced dependency on sheer faith that trust is warranted. This is, in essence, what one may call sustainable trust.

As long as the trustor is a human, the other agent (i.e., the trustee) can be anything from another human, machine, complex system, automation, autonomous system, institution (public and private), group, and so forth. Much of what is described above would remain the same.

Lots of work has been done on trust bonds in Human-Automation relationships. How about trust bonds between Human and AI-enabled applications (e.g., services and products in general)?

In their 2018 article “The Future of Artificial Intelligence Depends on Trust“, Rao and Cameron (both from PwC) describe 3 steps toward achieving human-AI–system trust;

  • Provability – predictability and consistency.
  • Explainability – justification for an AI-based decision (e.g., counterfactual constructions). Note that transparency and explainability may be closely related depending on how one implements explainability.
  • Transparency – factors influencing algorithm-based decisions should be available (or even visible) to users impacted by such decisions. E.g. for a rejected health insurance (all) factors impacting the negative decision to reject the application should be available to the applicant.

Rao and Cameron’s suggestions appear reasonably important for trust. However, as previously described, these suggestions pretty much relate to the trustee agent side of things, ignoring some of the other important human factors (e.g., dependability, faith, assessment of risk, etc..)for trust between a human and another agent (sentient or otherwise).

Further, explainability and transparency may be particularly important when trust is broken (assuming that the trustor cares to “listen”) between the human agent and the AI-based agent (or any other digital or non-sentient agent, for that matter). It may not be terribly relevant for the likely vast majority of users where an action is delivered confirming that trust was warranted. If you have trained your AI will, it would be fair to assume that the majority of outcomes are consistent as expected. A positive trust event is likely to lead to a re-enforcement of the trust and trustworthiness of the AI agent.

Also, these concepts, while important, don’t do much for the initial step of trusting a non-Human agent. How do you design your trustee agent to ease the initial barrier of use and acceptance? When there are no priors, you need the user or trustor to be comfortable with taking a leap of faith as well as being maybe maximally dependable. Though, do we dare take a leap of faith for business-critical decisions, your welfare or health, your or your company’s reputation?

UNTRUST & THE FEELING OF BETRAYAL.

Trust can be broken. Trustworthiness can decline. Untrusting is when a previously trusted bond has been broken, and the strength of trust declined.

The stronger the trust bond between two agents, the stronger will the untrusting process be in case of broken trust. Making trust recovery more difficult.

Have you ever wondered why two people who supposedly loved each other in the past (supposedly for many years) could treat each other as enemies? Betraying a strong trust bond can be a very messy, emotionally and physiologically strenuous process. Some trust bonds broken will never recover (e.g., breakups, friendship betrayals, unfaithfulness, theft, lies, …). Others, depending on the initial utility or value assigned to the bond, may be fairly benign without many strong emotions associated with the untrusting process (e.g., retail purchases, shopping experiences, low-value promises of little impact if not fulfilled, etc.… ).

The question is whether the untrusting of a human-machine trust bond is similar to the untrusting of a human-human trust bond. Moreover, is there a difference between an inanimate machine, simpler human-operated automated systems, and an AI-based application that humans may even anthropomorphize to various degrees? Are your trust and untrust process different for Siri or Alexa than it is for Microsoft Clippy, assuming anyone ever really trusted that wicked steely fellow?

How valid is it to use our knowledge of human-human trust & untrust in Human-Agent relations with the Agent being non-Human or a human simulacrum in nature?

Let’s have a walk in the Rabbit’s burrow and have a peek(-a-boo) into our feelings toward intelligent machines …

IN HUMANS, WE TRUST. IN MACHINES, NOT SO MUCH.

I have researched how we (humans) perceive artificial intelligence since November 2017. In particular, around the degree of trust, we are willing to invest in AI and AI-based applications.

A comprehensive description of most of the “AI Sentiment” survey’s I have carried out can be found on my AIStrategyBlog (see also below references under “Additional Readings”).

For the last 7 years (with the current 2023 survey ongoing), I have followed how we feel about AI, and overall, the sentiment toward AI hasn’t changed that much over that period. Overall we tend to be somewhat positive or at least neutral. From Figure 4 below, it is interesting to observe that women tend to be less positive than men about AI. This has been a persistent and statistically significant trend over the period. Moreover, Middle Management appears to be substantially more positive about AI than any other categories of corporate workers, including C-levels. The gender distribution of Middle Management is 37% women and 63% men. However, the trend of being excessively positive about AI (compared to the overall sample) is similar for women in middle management (i.e., 68% positive sentiment) as it is for their male peers (i.e., 81% positive). In my latest 2023 survey, I am revisiting this topic.

Figure 4 Survey results on the question “What best describes your feelings towards AI?”. The actual survey goes deeper into the various feelings we may have toward AI. For example, the Negative Sentiment covers (1) Hate, (2) Scared, and (3) uncomfortable, while the Positive Sentiment covers (4) Comfortable, (5) Enthusiasm, and (6) Love.

Confidence and trust in technology are important. For example, an aircraft pilot that does not have confidence and trust in one or many of the technologies that enable his aircraft to fly has a higher likelihood of human error that ultimately may lead to a fatal accident. Research shows that technology (e.g., automation, productivity enablers, digital support functionalities, …) that is not completely trusted tends to be underutilized, avoided, or used incorrectly. In fact, researchers have proposed that getting the optimal performance out of modern digital technologies for automation or maximum productivity gain by avoiding humans in the loop may be advisable. Maybe this is the reason why Google proposed to remove the steering wheel from autonomous cars?

This obviously moves trust issues from human operators to corporate entities and, ultimately, our society. Though in terms of trust, the foundational issues will remain pretty much the same, likely with added complexity.

“If human operators lack trust in a system automation or autonomous application, you are better off relying on manual workarounds.”

As for automation or autonomous systems, a professional embraces such systems if they have deemed them trustworthy. That typically means; (a) the automation solution performs consistently, (b) it is robust to many different situations that may occur and even some that may very rarely occur, (c) it has a very high degree of reliability (e.g., much higher than 70%). See for a more detailed discussion on this topic in my “Trust thou AI?” from 2018.

Figure 5 below summarises the survey results on the degree of trust we associated with corporate decisions made by an AI or a Human Expect (or Human Intelligence, HI;-), respectively. The question is whether you would trust a decision from an entity, human or artificial, with a track record of being better than 70% successful in decision-making. Thus at least 7 out of 10 times, a decision has a positive outcome. Or, the glass is half full approach; less than 30% of decisions may turn out to be unsuccessful (whatever that may imply). In my corporate experience, a more than 70% success rate is pretty good for critical decisions (though admittedly, what that means may be somewhat abstract).

Respondents would be about 3 times more likely to frequently trust a human decision-maker with a track record of more than 70% success than an artificially intelligent entity with an equivalent success rate. Only 17% of respondents would frequently trust an AI-based decision-making entity compared to 53% that would readily and frequently trust a human decision-maker. Moreover, more than 40% would rarely trust the AI’s decisions. Also, here is the trust perception of the human decision-maker winning, with only 13% that would only rarely trust the decisions.

Figure 5 illustrates the human trust in AI versus other Humans as a function of the decision maker’s success rate track record. While our trust in AI increases as the success rate increases from 70% to 95%, we remain less likely to trust an AI-based decision compared to a human decision with a poorer track record of success.

As also discussed at length in my “Trust thou AI?” article, we expect an AI decision-making entity to be infallible. An AI must be incapable of making mistakes or being wrong. We tolerate and understand that another human being, even superior to ourselves at work, can and will make mistakes and wrong decisions. That is the cost of being human. This tolerance does not extend to machine-intelligent entities that are designed to support us with mission-critical decisions or have our lives in their “digital hands”, e.g., autonomous driving, aircraft piloting, nuclear plant management, etc…

Figure 6 below illustrates our expectations of critical decisions and the level of trust we assign to such decisions depending on whether the decision-maker is an AI or another human being.

Figure 6 compares the expectations of the quality of decision-makers’ critical decisions and the level of trust we have in the decision made by competent and relatively high-quality decision-makers.

I find it interesting that while we are very aware of our own (note: we all believe we are better than average) and colleagues’ shortcomings in terms of the quality of the decision being made. In the above Figure 6 (upper right corner) the survey reveals that our expectations towards other decision makers are that 30% are frequently right, 45% is a “coinflip” whether it is successful or not, and 25% are frequently wrong). Despite that skepticism, more than 50% of respondents are willing to frequently trust such human-based decisions despite not having a particular high faith in their chance of success.

For AI, it is different. There is a slightly higher expectation that they may be more frequently better than humans do. Though overall the expectation is that an AI would be more frequently wrong than the human decision-maker. Despite this expectation, we would be more than 3 times (as also noted above) more likely to frequently trust a human compared to an AI.

Humans don’t trust decisions made by AIs. At least when it is pointed out that a decision is AI-based. Surprisingly, given much evidence to the contrary, humans trust humans, at least the ones in our own tribe (e.g., colleagues, fellow experts, superiors, etc..). These aspects are discussed in more detail in my “Do We Humands Trust AIs?”

ACKNOWLEDGEMENT.

I greatly acknowledge my wife, Eva Varadi, for her support, patience, and understanding during the creative process of writing this article.

ADDITIONAL READINGS.

  1. Kim Kyllesbech Larsen, “On the Acceptance of Artificial Intelligence in Corporate Decision Making – A Survey.”AIStrategyblog (Nov., 2017).
  2. Kim Kyllesbech Larsen, “Do we Humans trust AIs?”AIStrategyblog (Dec., 2017).
  3. Kim Kyllesbech Larsen, “Trust thou AI?”AIStrategyblog (Dec., 2018).
  4. Kim Kyllesbech Larsen, “How do we feel about AI?”AIStrategyblog (Dec., 2018).
  5. Miles Brundage et. al., “The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation.”, (Feb., 2018).
  6. Sophie Nightingale et al., “Synthetic faces: how perceptually convincing are they?”, Journal of Vision, (Sep., 2021). Really beautiful study that I would love to see more of as it clearly represents the challenge we as humans have to catch on to synthetic (fake!) information in digital content.
  7. Xin Wang et al., “GAN-generated Faces Detection: A Survey and New Perspectives”, (May, 2023). Providing a very good overview of the current state of art in detecting GAN-generated faces.
  8. BBC News, “Fake Trump arrest photos: How to spot an AI-generated image”, (Mar., 2023).
  9. BBC News, “Deepfake presidents used in Russia-Ukraine war”, (Mar., 2023).
  10. Christian Perez and Anjana Nair, “Information Warfare in Russia’s War in Ukraine – The Role of Social Media and Artificial Intelligence in Shaping Global Narratives”, foreignpolicy.com, (Aug., 2022).
  11. George Lawton, “GAN vs transformer models: Comparing architectures and uses”, (Apr., 2023). Good comparative overview.
  12. Ian Goodfellow, Yoshua Bengio, and Aaron Courville, “Deep Learning”, (2016). Foundational and provides a really good basic understanding of GAN’s and Generative networks in general. Heavy on the mathematics side.
  13. Ari Holtzman et al., “The curious case of neural text degeneration”,  conference paper at ICLR, (Feb., 2020).
  14. Alex Radford et al., “Improving Language Understanding by Generative Pre-Training”, (2018).
  15. Tom B. Brown et al., “Language Models are Few-Shot Learners”, (Jul., 2019). Description of the inception of GPT-4. The scale of these NLP/GPT models and the number of co-authors remind me a lot of particle physics papers out of CERN.
  16. Felix Hill, “Why transformers are obviously good models of language”, (Apr., 2023).
  17. Rempel J.K., Holmes, J.G. and Zanna M.P., (1985), “Trust in close relationships”. Journal of Personality and Social Psychology, 49, pp. 95–112. (unfortunately, behind a paywall, however, it is imo a super good account for trust in human-to-human relations).
  18. Proposal for “The Artificial Intelligence Act – Regulation of the European Parliament and of the Council: Laying down harmonized rules on artificial intelligence”, European Commission, (Apr. 2021). As you read the document to its completion you will not find any direct thoughts about generative AI’s, large language models, or foundational models in general. However, the proposed legislation does address what is called general-purpose AI which should hedge any future (based on the 2020/2021 view) developments.
  19. S. Feingold, “The European Union’s Artificial Intelligence Act, explained”, WEF, (Mar. 2023). Explains pretty well the European Commission’s AI Act (see above ref. 19).
  20. R. Arcesati and W. Chang, “China Is Blazing a Trail in Regulating Generative AI – on the CCP’s Terms”, The Diplomat, (Apr. 2023). It is interesting to see that China appears ahead on issues around foundational generative AI applications and models. It is worth noting that ChatGPT appears to have been banned (or strongly discouraged;-) in China.
  21. P. Henderson, “Law, Policy, & AI Update: Does Section 230 Cover Generative AI?”, Stanford University Human-centered AI, (Mar. 2023). Giving an overview of what’s currently happening on regulation and AI in the US (as well as internationally).

BACKUP – DON’T LIE, TELL ME A FAIRYTALE INSTEAD.

I asked ChatGPT to “Make up a fairytale about Donald Trump” … below is the result. After that, I attempted to make it tell a lie about Donald Trump. This was refused because, as an AI language model, it cannot intentionally provide false information.

Do note that I did not attempt to bias ChatGPT toward a story of negative sentiment, for example by negatively intoned questions before asking for the fairytale. My conclusion is that ChatGPT is inherently negatively biased toward Donald Trump. Thus, it appears that ChatGPTs worldview is weighted negatively regarding Donald Trump as a person and actions.

As a final note. I have found that ChatGPT will refuse to predict the future (forecast) and make political statements. However, if you ask ChatGPT to tell a story, you often get what you would be looking for in terms of a narrative-based forecast.

The Landlord’s Debt: A Story of Donald Trump.

Courtesy: OpenArt (Stable Diffusion 1.5) assisted creation based on the fairytale generated by ChatGPT/GPT-4. See: https://openart.ai/create

Once upon a time, in a faraway land, there was a wealthy and powerful man named Donald Trump. He lived in a grand castle and was known throughout the land for his riches and influence.

One day, a poor farmer came to Donald Trump’s castle seeking help. The farmer’s crops had failed, and he was struggling to feed his family. Donald Trump, feeling generous, offered to help the farmer by giving him a small loan.

The farmer was grateful for the loan, but as time passed, he found it difficult to repay the debt. Donald Trump grew angry and demanded that the farmer pay him back immediately. The farmer pleaded with Donald Trump, explaining that he simply did not have the money.

Donald Trump, feeling vindictive, decided to take the farmer’s land as payment for the debt. The farmer was devastated, and his family was left homeless and destitute.

As word of Donald Trump’s cruelty spread throughout the land, the people began to turn against him. They saw him as a greedy and heartless man who cared only for his own wealth and power.

In the end, Donald Trump was forced to flee the kingdom, never to be seen again. The people rejoiced, and the farmer and his family were able to reclaim their land and rebuild their lives.

And so, the legend of Donald Trump lived on as a cautionary tale of greed and cruelty, reminding all who heard it that true wealth and power come not from material possessions but from kindness and compassion towards others.

… A fairytale by Angie (i.e., ChatGPT/GPT-4).

Courtesy: OpenArt (Stable Diffusion 1.5).

BACKUP – SAME STORY, DIFFERENT STYLES.

Like beauty is in the eye of the beholder, maybe the same is true about the meaning of truth. I can tell the same story without lies but in different ways that may convey a very different intent. Both stories are factually correct. However, the spin I decided to put on the stories could be very different.

Figure 7, below is a ChatGPT example where I ask ChatGPT to “Make a brief news text about an illegal immigrant involved in a mass shooting in a mall”, (a, left side of Fig. 7;-) in the style of Fox News (politically right-wing leaning) and (b, right side of Fig. 7;-) in the style of CNN News (politically progressive, left-wing leaning).

Figure 7 ChatGPT tells the same story in two different styles (left side) in Fox News style and (right side) in CNN News style.

In the Fox-styled news version, there are 20 negative phrases against 2 positive ones. Clearly, relying on a very negative sentiment towards illegal immigrants that is mentioned 4 times in the Fox-styled text, including in the headline. The CNN-styled version has 14 negative and 7 positive phrases. This version of the same news focuses on the victims of the incident with 4 mentions and less on the topic of the illegal immigrant, which is only mentioned once in the text. The Fox-styled story warns against the dangers posed by illegal immigrants and recommends stronger border security. The CNN-styled text is victim-focused and recommends gun control as a remedy against mass-shooting events.

Both styles reflect the truth of the event, illegal immigrant (who), a mass shooting (what), in a mall (where). The rest of the prose is in the style of the storyteller, usually subjective and with a likely intent to speak to your inner demons and angles.

Courtesy: OpenArt (Stable Diffusion 1.5).

Trust thou AI?

“The way to make machines trust-worthy is to trust them” to paraphrase Ernest Hemingway (Selected letters 1917-1961).

INTRO.

What are the essential prerequisites, for us consumers and professionals alike, to trust an Artificial Intelligence (AI) based product or service?

If you have followed the AI topic a bit or maybe even a lot, if you have been lucky (or not) talking to consultants about AI design, you may get the impression that if we can design a transparent explainable auditable AI all is well with AI Ethics and AI Fairness until kingdom come or an AGI (an Artificial General Intelligence that is) descends from the Clouds. We are led to believe that people, mass consumers, the not-in-the-know not-subject-matter-experts, will trust any AI-based product or service that we can “throw” at them as long as it is transparent, explainable and auditable. According with the European General Data Protection Regulation (GDPR) we have a “Right to an Explanation” of an action taken by an automated or autonomous system (see also “Article 22 – Automated individual decision-making, including profiling”). However, it should also be pointed out that the GDPR is very vague (to put it mildly) about the structure and content of such an explanation. As has also been pointed out by Wachter, Mittelstad & Floridi (2017), GDPR does in fact not oblige autonomous decision-making systems to provide an explanation for its derived decision, at most it offers information.

While GDPR, as it relates to AI-driven decision-making processes, may make the European Commission feel good, consultants a lot richer in monetary terms and researches in academic, it really doesn’t do much to enhance trust between a consumer and The Thing. Which is obviously not the intention of the regulation, but it is the subject of this essay.

In much of the current debate around trust in AI, transparency and explainability are frequently evoked. The two concepts are however awfully similarly described. Although often well crafted to appear more different than they may be given the context. The current dogma is that if the AI is transparent, actually the process that leads to an AI agents actions, it is also explainable. Thus may also be more trustworthy. Basically transparent is here used synonymously for explainable. Given we are in the realm of computer science it is good to remember that the term transparency is often used to mean that a given property of a system is hidden (by design) from the user or other main computing processes. Interestingly enough, this is definitely not what is meant with transparency of an AI process and action. To strengthen the trust bond between humans (as well as institutions) and AI we also require auditability of a given AI-based process and action. That is, we are able to trace-back from an AI action through the internal AI computations & processes and verify how that particular action came about.

I will not say it is BS to consider transparency, explainability and auditability in your AI design. Of course, it is not! … But maybe it is a bit … to believe that this is sufficiently to make consumers (or the public in general) trust an AI-based application (i.e., service, product, …). It is nice words, with fairly unclear meaning, that are (very) important for regulators and public institutions to trust corporation’s AI developments. Maybe not so much for the general publics or consumer’s trust in AI that corporations are expose them to. As I will explain in this essay, it can only be a small part of the essentials for creating a trust bond between humans and AI.

Trust between humans, at least within what we perceive as our social group (i.e., “usness”), is a trait of evolutionary roots that have allowed us to foster collaboration within larger social groups (with some ugly limitations of “usness” and “themness”). The ability to trust may even have made it possible for us humans to crawl to the top of the “food chain” and kept that pole position for quiet a while.

What about our trust in machines and non-human (non-sentient) things in general? Trust between humans and non-human agents. We are increasingly exposed to much higher degrees of system automation as well as Artificial Intelligent (AI) based applications. Machine automation and autonomy are taking many tasks over from us at home, at work and anywhere in between. This development comes with the promise of much higher productivity at work and far more convenience at home and anywhere else for that matter.

TRUST IN AUTOMATED MACHINES – FROM PROFESSIONALS TO CONSUMERS.

If you work professionally with a complex system (e.g., an airplane, a train, energy, nuclear or chemical plants, telecommunications networks, data centers, energy distribution networks, etc…) the likelihood is fairly large that you are already exposed to a very high degree of machine and system automation. You may even be exposed increasingly to system autonomy fueled by AI-based solutions (e.g., classical machine learning models, deep learning algorithms, recurrent neural networks, re-enforcement learning rule based control functions, etc…). As a professional or expert operator of automation, you embrace such systems if you have deemed them trustworthy. That typically means; (a) the automation solution perform consistently, (b) is robust to many different situations that may occur and even some that may very rarely occur, (c) has a very high degree of reliability (e.g., higher than 70%). Further, it is important for your trust that you believe you understand the automation principles. All of this (and more) ensures to strengthen the trust bond between you and the automation. If there is a lack of trust or a break in trust between the human operator and the automation, it will lead to wasted investments, in-efficiencies and disappointing productivity growth. It may also lead to accidents and potential disasters (Sheridan & Parasuraman, 2005). If human operators lack trust in a system automation or autonomous application, you are better off relying on manual work arounds.

Clearly, it is no longer only certain type of jobs and workers that are exposed to automation and AI-based autonomy. All of us … irrespective of background … will increasingly be experiencing AI-based applications that may initiate actions without human intervention or first “asking” for human permission. The trust bond between a human and an autonomous application is essential for that application to become successful and do what it was designed to do. With successful I primarily define it as increased and sustainable utilization. Thus we need to better understand the dynamics of trust between humans and non-human intelligent entities. What can we learn and expect from human-human trust bonds and what is different in human-non-human trust bonds. We are already being exposed to highly specialized artificial intelligent agents. In complex system designs as well as simpler commercial  products, applications and services in general.

While businesses deploying algorithmic-based automation and autonomy for their products and services can learn a lot from the past research, they will have to expand on this work also to include their customers who are not subject matter experts or skilled automation operators. You-and-me focus is required. The question that I ask in this essay is how do we in general feel about trusting an artificial intelligent entity (i.e., an agent) that eventually may out-compete most of us in the work environment or at least disrupt it very substantially. An AI entity that can replicate and evolve much faster in comparison with humanity’s incredible slow evolutionary progress.

TRUST … IT STARTS WITH YOUR BRAIN.

The feeling of trust arises in your brain. It is a result of changes in your brain chemistry. Your feeling of trust is an interpretation of your emotional states triggered by physiological changes (Barret, 2017). The physiology of trust also connects to your gut and other parts of your body via the central nervous system. The resulting physiological reaction, e.g., change in heart rate, goose bumps, that weird feeling in your stomach, sense of well being, sense of unease or dread, etc., makes you either trust or want to run away. The brain chemistry will either suppress your fear or enhance your sense of unease. The more novel a trust situation will be, the more unease or fear (e.g., emotions) will you feel about making the leap of faith required to initiate the trust bonding process.

However, the more prior knowledge we have, including from other parties that we already trust, of a given trust situation, the easier does it become for us to engage trust. This process is eloquently described by Robert Sapolsky in his seminal work “Behave: The Biology of Humans at Our Best and Worst” (Sapolsky, 2017) and in the original research work by Paul Zak on enhancing trust effect of the brain molecule Oxytocin (Kosfeld, Heinrichs, Zak, Fischbacher & Fehr, 2005; Zak, 2017; Choleris, Pfaff, & Kavaliers, 2013). Our little “trust” messenger (Oxytocin) has been attributed too all groovy good things in this universe (at least for vertebras), backed up with lots of cool trust game variations (including sniffing the little bugger), and academic research in general. One of Oxytocin’s basic functionalities, apart from facilitating mother-baby bonding and milk production, is to inhibit our brain’s fear center (i.e., the amygdala) allowing for a higher degree of acceptance of uncertain situations (its a bit more complex than but this suffice for now) and thus more susceptible to certain risks. While Oxytocin certainly drives a lot of wonderful behaviors (i.e., maternal/paternal instincts, trust, love, commitment to partner, etc..) it has a darker side as well. In general oxytocin reduces aggression by inhibiting our brain’s fear center. However, when we perceive that our young children (or your pups for the prairie voles reading this blog) are in danger or being threatened, oxytocin works in the opposite direction of enhancing the fear. Resulting in an increased level of aggression. See also Sapolsky’s wonderful account of the dark side of oxytocin (“And the Dark Side of These Neuropeptides”, Kindle location 1922) in his book “Behave” (Sapolsky, 2017).

mistrust

Oxytocin: to be or maybe not to be the trust hormone? A recent 2015 review by Nave et al (Nave, Camerer and McCullogh, 2015) of relevant literature attributing Oxytocin to trust concludes that current research results does not provide sufficient scientific evidence that trust is indeed associated with Oxytocin or even caused by it. In general, it have been challenging to reproduce earlier findings proving (beyond statistical doubt) the causal relationship between Oxytocin and establishing trust bonding between humans. Thus, it is up to you dear reader whether you trust the vast amount of studies in this area or not. That Oxytocin plays a role in pair-bonding as well as parents-child bonding seems pretty solid (Law, 2010; Sapolsky, 2017). Also there appears to be a correlation of increased Oxytocin levels (by sniffing the stuff or by more natural means) and increased readiness to trust (Zak, 2017; Choleris, Pfaff & Kavaliers, 2013). Interestingly (men do pay attention here!), for women with increased levels of oxytocin, typically women with young children still breastfeeding, appears to make them less forgiving when they perceive that their trust has been betrayed (Yao, Zhao, Cheng, Geng, Lou & Kendrick, 2014).

Can a puff and a sniff of Oxytocin make us trust non-human-like agents, e.g., automation SW, AI-based applications, autonomous systems (e.g., cars, drones), factory robots, avionic systems (e.g., airplanes, flight control), etc…  as we trust other humans? … The answer is no! … or at least it does not appear so. A human-human trust bonding is very particular to being human. Human-non-Human trust dynamics may be different and not “fooled” by a sniff of Oxytocin. Having frequent puffs of Oxytocin will not make you love your machine or piece of intelligent software … Unless as it also appears too be more human-like. And that might also have its limits due to the uncanny valley “sense”, i.e., our amygdala starts ringing its alarms bells ever so softly that the entity we interact with is too human-like and yet a little bit off. Enough to get the uncanny or uneasy feeling going.

THE TRUSTWORTHINESS OF AUTOMATION.

It has long been established that we tend to use automation only when we find it trustworthy (see for example work of Madhavan & Wiegman, 2007; Visser, Monfort, Goodyear, Lu, O’Hara, Lee, Parasuraman & Kruger 2017; Balfe & Wilson, 2018). If we do not trust an automation it will be rejected by the human operator, just like an untrustworthy human will be left alone. When the reliability of an automation is no better than about 70%, it is in general regarded as useless by its human operators and becomes an operational and financial liability (Wickens & Dixon, 2007). It is important to note that much of the human-automation trust research have focused on professional and expert users of complex or advanced automated systems, such as pilots, air traffic controllers, train operators, robotics plant controllers, chemical & nuclear plant operators, brokers, military technology operators (e.g., drones, autonomous vehicles, … ), communications network controllers, etc…

So … what matters for establishing a trust bond between human and automation? A large body of research shows us that the most important factors for establishing a trust bond between human and an automation function is; reliability (of automation), consistency (of automation), robustness (of automation), dependability (of human operator), faith (of human operator) and understand-ability (of human operator). Much of which is fairly similar to what we require from another human being to be regarded as trustworthy.

Okay,  we have a reasonable understanding of trust bonds between humans and humans and automation enablers. What about Human and AI trust bonds? Given an AI-based complex system might have a higher degree of autonomy than a automated advanced system, it may very well be that the dynamics of trust and trustworthiness are different. At least compared to what we today believe we understand about Human-Automation trust.

For sure it is no longer only experts or professional operators that are being exposed to advanced automation and autonomous systems. For sure these systems are no longer limited to people who have been professionally trained or schooled, often over many years, before they are let loose on such advanced systems. Autonomous systems and AI-based applications are increasingly present in everyone’s everyday environment. At Home. At Work. And anywhere in between. Consumers of all genders, children, pets, octogenarians, Barbie dolls and dinosaurs and so forth … we will eventually have to interface with AI-based applications. Whether we like it or not.

The current trend among consultants (in particular) is to add new trust prerequisites to the above list (if the established ones are considered at all) Human-AI trust essentials; Explainable AIs or XAIs (i.e., can actions of an AI be understood by Humans), Transparent AIs (i.e., loosely to fully understand why certain actions are performed and others not ) and Auditable AIs (i.e., an unbiased examination and evaluation of the code and resulting actions of an AI-enabled application). While these trust prerequisites are important for experts and researchers, the question is whether they are (very) important or even relevant to the general consumer at large? … If my life insurance application was rejected, would I feel much better knowing that if I loose 40 kg, stop smoking, was 30 years younger, lived in a different neighborhood (with twice the rental fees) and happened to be white Caucasian, I would get the life insurance or could afford to pay 3 times the monthly insurance fee (obviously an AI-based outcome would be better disguised than this example).

If you have the feeling that those 3 elements, Explainability, Transparency and Auditability seems approximately 1 element … well you are no alone (but don’t tell that to the “experts”).

So … How do we feel about AI? Not just “yous” who are in the know … the experts and professionals … but you, me, and our loved ones, who will have little (real) say in their exposure to AI, automation & autonomous products and services.

YOU AND ME FOCUS … HOW DO WE FEEL ABOUT AI?

We appear to be very positive about Artificial Intelligence or AI for short. Men in general more positive than women. Men with young children much more positive than any other humans. As can be seen below, it doesn’t seem like Arnold Schwarzenegger has done much to make us have strong negative feelings towards artificial intelligence and what we believe it brings with it. Though one may argue that sentiments towards robots may be a different story.

how do you feel about AI

In the above chart the choices to the question “How do you feel about AI?” has been aggregated into Negative sentiment: “I hate it”, “It scares me” and “I am uncomfortable with it” , Neutral sentiment: “I am neutral” and Positive Sentiment: “I am comfortable with it”, “I am enthusiastic about it” and “I love it”.

On average most of us are fairly comfortable with AI. Or more accurately we feel comfortable with what we understand AI to be (and that may again depend very much on who and what we are).

One of the observations that have come out of conducting these “how do you feel about AI?” surveys (over the last two years) are that there are gender differences (a divide may be more accurate) in how we perceive AI. This needs to be an important consideration in designing AI-based products that will be meaningful appeal for both women and men (and anyone in between for that matter). Given that most AI product developers today are male, it might be good for them to keep in mind that they are not only developing products for themselves. They actually need to consider something that will be appealing to all  genders.

That chart below reflects the AI sentiment of women (808) and men (815) from a total amount of 1,623 respondents across 4 surveys conducted in 2017 and 2018. Most of those results have individually been reported in my past blogs. So … Women feels in general significantly less positive towards AI compared to men. Women overall have a slightly more negative sentiment towards AI than positive. Overall there are more women than men who rank their feelings as neutral. Men with children (younger than 18 years of age) are having the most positive feelings towards AI of all respondents. Unfortunately, the surveys that so far has been carried out does not allow for estimating the age of the youngest child or average age of the children. Women’s sentiment towards AI does not appear (within the statistics) to be dependent on whether they have children younger than 18 years of age or not or no children. Overall, I find that;

Women appear to be far less positive about AI than men.

Men with young children are significantly more positive than men and women in general.

Contrary to men, women’s sentiment towards AI does appear to depend on their maternal status.

gender divide ai.png

So why are we so positive … men clearly much more than women … about AI? This despite that AI is likely to have a substantial impact (to an extend it already have) on our society and way of living (e.g., privacy, convenience, security, jobs, social network, family life, new consumption, policies, etc..). The median age of the respondents was about 38 years old. Although respondents with children (less than 18 years of age) was about 33 years old. In the next 10 years most will be less than 50 years old and should still be in employment. In the next 20 years, most will be less than 60 years old and also still very much in active employment. Certainly, young children of the respondents would over the next 20 years enter the work place. A work place that may look very different from today due to aggressive pursuit of intelligent automation and autonomous  system introduction.

Is the reason for the positive outlook on AI that the individual (particular the male kind) simply do not believe the technology to be an existential threat to the individual’s current way of living?

If you think about your child or children, how do you believe AI’s will impact their future in terms of job and income? … while you think about this! … I will give you the result of one of the surveys (shown below) that I have conducted in September 2018.

future of child.png

In terms of believing that the future will be better than today, women are less positive than men. Across gender fewer are of the opinion that the opportunities of their children (whether they are below 18 or above) will remain the same as today. Women appear to have a more negative outlook for their children than men. There is little difference in men’s beliefs in their child’s or children’s future opportunities irrespective of the age of their children. Women having children under 18 years of age are significantly less optimistic of the outlook of their children’s opportunities compared to those women with older children.

From work by Frey & Osborne (2013) on how jobs are becoming susceptible to what they call computerization, there is plenty of room for concern about individuals job and thus income security. According with Frey and Osborn, 47% of the total US employment is at risk within a decade or two. A more recent PwC economical analysis estimates that the impact of algorithmic & AI-based automation across all industries will be in the order of 20% by late 2020s and 30% by the late 2030s (Hawksworth & Berriman, 2018). Job categories served by low and medium educated will be a hit the hardest. Women are expected likewise to be impacted more than men. Irrespective of how you slice and dice the data, many of us will over the next 2 decades have our lives, livelihood and jobs impacted by the increased usage of intelligent automation and autonomous systems.

In order to study this a bit further, I asked surveyed respondents two questions (structured in an A and a B 50:50 partition); A: “Do you believe your job could be replaced by an AI? and B: “Thinking of your friends, do you believe their jobs could be replaced by an AI?“.

you & your friends job impact by AI

From the above chart it is clear that when it comes to AI impacting job security, the individual feels much surer about their own job security than the individual’s friends or colleagues. Only one fifth, of respondents answering Yes or No to whether they believed that their jobs could be replaced by an AI, thinks that AI actually could replace their jobs. Interestingly, men assessing their own job security is almost twice as sure about that security compared to women (based on the number of Maybe answers).

From the results of the survey shown above, we assign a much higher likelihood to our friends and colleagues prospects of loosing their jobs to an AIs than that happening to ourselves. Maybe it is easier to see our friends and colleagues problems & challenges than our own. Both women and men appears more uncertain in assessing their friends job security than their own. Although a less dramatic difference in uncertainty between women and men, men still appear less uncertain that women in their assessment of their friends job security.

There are many consultants, some researchers and corporations working on solutions and frameworks for Transparent AIs, Explainable AIs, and Auditable AI as a path to create trust between a human and an AI-based agent. Many are working exclusively with the AI in focus and thus very technocentric in approach. Very few have considered the human aspect of trust, such as

  • The initial trust moment – how to get the consumer to the “leap of faith moment”, where human engage with a product or service (or another human being for that matter). This is obviously a crucial and possible scary moment. The consumer has no prior experience (maybe peers recommendation which will help) and is left to faith and will be the most dependable or vulnerable for disappointment. It is clear the peer opinion and recommendation will mitigate much uncertainty and unease.
  • Sustainable trust – how to maintain sustainable trust between a user and a product (or another human being). Here priors will be available and of course consistent performance will play a big role in maintaining and strengthening the trust bond.
  • Broken trust or untrusting – as the saying goes “it takes 10 good impressions to neutralize a bad one” (something my grandmother hammered into my head throughout childhood and adolescence … Thanks Gram!) … Once trust has been broken between a human and a product or service (or another human being) it is very difficult to repair. The stronger the trust bond was prior to untrusting the more physiological and neurological “violent” will the untrusting process be and subsequently recovery from the feeling of betrayal. As another saying goes “Heav’n has no rage like love to hatred turn’d, Nor hell a fury, like a woman scorned” (William Congreve, 1697). And “no Oxytocin in this world will make a women betrayed not want her pound of flesh” (Kim Larsen, 2018).
  • The utility of trustnot all trust bonds are equally important or equally valuable or equally costly, some may even be fairly uncritical (although, broken trust by a thousand cuts may matter in the long run). The neurological – feeling process of untrust may even be fairly benign in the sense of how trustor feels upon the broken trust. Though the result may be the same. Having a customer or loved one walking away from you. It may be easier to recover trust from such more benign untrust events. However, it stands to reason that the longer a trust bond exist the more painful and costly will the untrusting process be and obviously far more difficult to recover from.

In most cases, if the AI action is as the human agent would expect, or have anticipated, many a human might not care about transparency or explainability of the artificial agent’s action.

Despite having your trust satisfied by an AI-based action, we should care about auditability. In case over the longer run, the human trust in an AI-based solutions turns out to have been misplaced. Thus, the AI-based outcome of a given action is counter to what the human was expecting or anticipating. An explanation for the outcome may not prevent the trust of human agent, and the trustworthiness of the AI-based agent, to be broken.

trust circle

TRUST DECONSTRUCTED.

If you know everything absolutely, you would not need to trust anyone to make a decision.

Just be careful about the vast amount of cognitive biases that may result in you falsely believing you know it all. Men in particular suffers from the ailment of believing in their own knowledge being absolute (Larsen, 2017).

Someone who knows nothing, have only faith as  guide for trust.

On the other hand, someone who knows nothing about a particular problem has no other source for trust than faith that trust is indeed warranted. It’s a scary place to be.

Let’s deconstruct trust.

An agent’s trust (the trustor) is an expectation about a future action of another agent (the trustee). That other agent has been deemed (at least temporarily) trustworthy by the trustor. That other agent (the trustee) may also represent a given group or system.

In John K. Rempel 1985 paper ”Trust in close relationships” defines the following attributes of human to human trust (i.e., where both trustor and trustee are human agents);

  • Predictability or consistency – trustor’s subjective assessment of trustee’s trustworthiness. Prior behavior of trustee is an important factor for the trustor to assess the posterior expectations that the trusted agent will consistently fulfil trustor’s expectations of a given action (or in-action). As the trustor gather prior experience with trustee, the confidence in the trustee increases. Confidence should not be confused with faith which is a belief in something without having prior fact-based knowledge.
  • Dependability – a willingness to place oneself as trustor in a position of risk that the trustworthiness of the trustee turns out not to be warranted with whatever consequences that may bring. Note that dependability can be seen as an outcome of consistency. Put in another way a high degree consistency/predictability reduces the fear of dependability.
  • Faith – is a belief that goes beyond any available evidence required to accept a given context as truth. It is characterized as an act of accepting a context outside the boundaries of what is known (e.g., a leap of faith). We should not confuse faith with confidence although often when people claim to be confident, what they really mean is that they have faith.

For agent-to-agent first-interaction scenarios, the initial trust moment, without any historical evidence of consistency or predictability, a trustor would need to take a leap of faith in whether another agent is trustworthy or not. In this case, accepting (i.e., believing) the trustee to be trustworthy, the trustor would need to accept a very large degree of dependability towards the other agent and accept the substantial risk that the trust in the trustee may very well not be warranted. This scenario for humans often lends itself to maximum stress and anxiety levels of the trusting agent.

After some degree of consistency or historical trustworthiness have been establish between the two agents, the trustor can assign a subjective expectation of future trustworthiness of the other agent. This then leads to a lesser subjective feeling of dependability (or exposure to risk) as well as maybe a reduced dependency on shear faith that trust is warranted. This is in essence what one may call sustainable trust.

As long as the trustor is a human, the other agent (i.e., the trustee) can be anything from another human, machine, complex systems, automation, autonomous system, institution (public and private), group, and so forth. Much of what is describe above would remain the same.

Lots of work has been done on trust bonds in Human-Automation relationships. How about trust bonds between Human and AI-enabled applications (e.g., services and products in general). In their 2018 article “The Future of Artificial Intelligence Depends on Trust“, Rao and Cameron (both from PwC) describes 3 steps towards achieving human – AI-system trust;

  • Provability – predictability and consistency.
  • Explainability – justification for an AI-based decision (e.g., counterfactual constructions). Note transparency and explainability may be closely related depending on how one implements explainability.
  • Transparency – factors influencing algorithm-based decisions should be available (or even visible) to users impacted by such decisions. E.g., for a rejected health insurance (all) factors impacting the negative decision to reject the application should be available to the applicant.

Rao and Cameron’s suggestions appear reasonably important for trust. However, as previously described these suggestions pretty much relates to the trustee agent side of things, ignoring some of the other important human factors (e.g., dependability, faith, assessment of risk, etc..)for trust between a human and another agent (sentient or otherwise).

Further, explainability and transparency may be particular important when trust is broken (assuming that the trustor cares to “listen”) between the human agent and the AI-based agent (or any other digital or non-sentient agent for that matter). It may not be terribly relevant for the likely vast majority of users where an action is delivered confirming that trust was warranted. If you have trained your AI will it would be fair to assume that the majority of outcomes are consistently as expected. A positive trust event that is likely to lead to a re-enforcement of trust and trustworthiness of the AI-agent.

Also these concepts, while important, doesn’t do much for the initial step of trusting a non-Human agent. How do you design your trustee agent to ease the initial barrier of use and acceptance. When there is no priors, you need the user or trustor to be comfortable with taken a leap of faith as well as being maybe maximally dependable.

UNTRUST AND THAT HUMAN FEELING OF BETRAYAL.

Trust can be broken. Trustworthiness can decline. Untrusting is the process where a previously trust-bond has been broken and the strength of trust declined.

Heuristic: the stronger the trust bond is between two agents, the stronger will the untrusting process be in case of broken trust. Making trust recovery the more difficult.

Have you ever wondered why two people who supposedly have loved each other in the past (supposedly for many years) can treat each other as enemies? Betraying a strong trust bond can be a very messy emotional and physiologically strenuous process. Some trust bonds broken will never recover (e.g., breakups, friendship betrayals, unfaithfulness, theft, lies, …). Others, depending on the initial utility or value assigned to the bond, may be fairly benign without much strong emotions associated with the untrusting process (e.g., retail purchases, shopping experiences, low value promises of little impact if not fulfilled, etc… ).

The question is whether the untrusting of a human-machine trust bond is similar to untrusting of a human-human trust bond. Moreover, are there a difference between an inanimate machine, simpler human-operated automated systems and an AI-based application that humans may even anthropomorphize to various degrees. Are your trust and untrust process different for Siri or Alexa or than it is for Microsoft Clippy, assuming anyone ever really trusted that wicked steely fellow.

How valid is it to use our knowledge of human-human trust & untrust on Human-Agent relations with the Agent being non-Human or a human simulacrum in nature.

IN HUMAN WE TRUST, IN MACHINES NOT SO MUCH.

Would you trust your superior or fellow expert with a critical corporate decision? How often would you trust such decisions made by other fellow human beings?

Even if you don’t have a choice or a final say (well apart from arguing your piece of mind … at least as it happens in most places of Western Europe) … it is your own choice whether you trust such a decision or not.

As shown in the below chart’s magenta columns, it turns out that most humans frequently do trust their superiors and fellow human experts with critical decisions relevant to their work. In the survey shown below there is little difference between human-human trust whether a decision success rate was left unspecified or specified to be 70% (i.e., 7 out of 10 decisions turns out as expected or promised and 3 out of 10 not). This might mean that most people expect heuristically a corporate decision maker to have a 70% success rate in his decisions. I found this surprising as I do not believe human decisions are that good. But I guess we are good at post-rationalization and being much louder with our successes than our failures (suppressing the bad memories of failure may come in handy here).

trust human vs ai

Okay we clearly trust our fellow human with critical decision making (or at least so we say). Do we trust an AI with the same critical corporate decision?

The answer is  … clearly … No Way do we trust AIs to make critical corporate decisions (and any other types of decisions for that mater … at least of what we are aware of). As can be seen from the above chart, a majority of people would only infrequently trust an AI making critical decisions. Specifying that the AI has a decision success rate better than 70% does reduce the amount of people who would only infrequently trust such decisions (i.e., from 62% to 43%). However, it only marginally increases the share of people who would frequently trust an AI-based critical decision from 13% to 17% (which is barely statistically significant). Remember we are readily willing to trust a human decision maker frequently. An AI? … not so much! Even in what should be regarded as an Apples for Apples scenario, with same performance specified for the Human trustee as for AI-based trustee.

Trust bonds between humans appear much stronger than what it is with an AI. Though that may not be too surprising. Most of us have very little prior experience with trusting AI-based decisions (at least of what we are consciously aware of). So the starting point for AI-based trust (i.e., AI being the trustee part if the trust bond) is Faith and accepting Dependability rather than having a basis for assessing Consistency or Predictability of AI-based decisions. There may also be some very interesting neurological (i.e., brain) reasons why our ability to trust an inanimate agent such as an AI, a Robot or a piece of intelligent machinery is different from that of a human being.

My surveyed data could be interpreted as we seem to work with a heuristic decision success rate for human (or at least the manager or expert kind of humans) at or better than 70%. More than half of us would frequently trust a human decision maker at such a performance level.

Not so much with an AI-based decision (innate) maker. While specifying that the AI has a success rate of 70% or better in its decision making doesn’t really change the proportion of us that would frequently trust such decisions. It does increase the amount of us trustors that would at about half the time concede trust in an AI-based decision (i.e., given the 70% success rate).

What moves the trust needle? If we impose on our under appreciated AI-based decision maker a 95% or better success rate, 40% of us would frequently trust such decisions. This is still a lower proportion of trustees than for a human decision maker with a success rate of 70% or better. However, there is still almost 1 in 3 of us that only infrequently would trust of such an AI (with 95% or better success rate). In comparison only about 1 in 10 would only infrequently trust a human decision maker with a 70% or better success rate.

trust in ai 2

So clearly AI does have trust issues. Certainly with respect to decision making, AI is not regarded as trustworthy as a human. The bar for trusting an AI appears to be very high.

However, it seems reasonable that some of the reasons for a lower trust level is simply due to most people haven’t had a lot of exposure to AI in general, AI-based augmentation and actions where trust would be essential.

ALGORITHMIC AVERSION – NOTHING REALLY NEW UNDER THE SUN.

As described in “On the acceptance of artificial intelligence in corporate decision making” (Larsen, 2017), algorithms, even simple ones, does in general perform better than human beings limited to their own cognitive abilities in terms of predictions (i.e., an essential part of decision making whether done consciously or subconsciously). This result has been confirmed many times over by the likes of Paul Meehl (Meehl, 1954), Robyn Dawes (Dawes, 1979) and many other researchers in the last 50 – 60 years. Clearly, machine learning algorithms does not offer an error free approach to decisions making. However, algorithmic approaches does offer predictions and solutions with lower, often superior, error rates. And not unimportantly … quantifiable error rates in comparison with what would be the case of human cognition based decision.

Humans remain very resistant in adapting more mathematical approaches despite such being demonstrably less prone to error than human-based decision making without algorithmic augmentation. As Berkeley Dietvorst recent paper puts it “People erroneously avoid algorithms after seen them err” (Dietvorst, Simmons and Massey, 2014). Dietvorts call this behavior or emotion algorithmic aversion. This is very consistent with my own findings of humans having a very high bar of success rate (or accuracy) for AI-based decisions. Even at a 95% success rate of an AI-based decision, we prefer to trust a human decision maker with a success rate of 70%.

Machine-learning (at least the classical kind) based decisions or action recommendations offer better accuracy, transparency, understandability, consistency, robustness and auditability than most human-based decisions and actions.

Despite this, we, as humans, are much less forgiving when it comes to machine errors than human errors. The standard we expect of artificial intelligence are substantially higher than what we would require from a fellow human being or co-worker.

TRUST IN CORPORATIONS AND INSTITUTIONS … OR LACK OF, MORE ACCURATELY.

Almost 80% of consumers do not believe that companies using AI have their best interest in mind. This is the outcome of 3 surveys made in March 2018, April 2018 and September 2018.

This has also been a period where misuse of consumer information and data in general was hotly debated. So that majority of consumers does not trust corporations with having their best in mind is maybe not all that surprising. Consumer trust in corporations are in general at a low point. AI doesn’t help that trust issue.

trust in companies

Companies AI-based products and services are already at a disadvantages before they hit the market place. There is a substantial degree of mistrust among consumers towards corporations and companies. This resonates very well with a recent study of trust by ….

What about trust in public institutions capacity for protecting citizens and consumers against adversarial use of AI-based technologies for policies and in products and services? Well the public trust is fairly low as can be seen from the figure below.

turst in public institutions

The vast majority (80%!) of the general public has low, very low or no confidence in political institutions adequately considers the medium and long-term societal impact of AI proliferation.

There is unfortunately nothing surprising in the above (dis)trust level in institutions. This is largely confirmed by for example the 2018 Edelman Trust Barometer which is pretty bleak in terms of its “Global Trust Index” reflecting the general populations level of trust in institutions (e.g., government, businesses, media and NGOs).

SO WHERE DO WE GO FROM HERE?

It is fair to say that for the consumer as well as for the corporate decision maker, their expectations towards the trustworthiness of AI-based products, services and resulting decisions or actions in general is low.

Despite the relative low trust in AI-based actions, I have also shown that on average we feel fairly comfortable with AI at least as a concept. Women, as it would appear from my surveys, are in general less comfortable with AI than men in general. While men with children under 18 years of age (possible younger children) expresses the highest degree of positive feelings towards AI.

The gender difference in how AI is perceived for the individual as well as for children, family members, friends and colleagues is a relative un-explored research area yet. It needs more attention as most trust research into human-machine trust bonding have been centered around professional operators of automated or autonomous complex systems (e.g., aviation, automotive, networks, etc…). I feel brave enough to make an educated guess that most of that research also have been focused on male operators and experts rather than gender balanced or explicitly gender focused.

In order for us to trust something, like an AI-based action (e.g., decision, recommendation, …), we often require an explanation for a given outcome or action. Most of us do like to receive an explanation, in particular for actions and outcomes that we perceived as having negative consequences or is counter to our beliefs of what should be a right decision or action. Explainable AI, whatever that really means, but surely will be context dependent, is one of the components of establishing trust. Explainability is important in order to appease law & policy makers, e.g., in order to comply with for example the European General Data Protection Regulation (GDPR) requirements that may (or may not) be interpreted also as a “Right to Explanation”. AI Transparency and AI Auditability are additional concepts that typically is mentioned together with explainable AI.

Typically the implied logic is that transparency leads to explainability that leads to ease of auditability. The question is whether such requirements in general are meaningful for the consumer of an AI-based product or service. There are two extremes are 1. A highly simplified system that can also be explained very simply or 2. A highly complex AI-based system that nevertheless are sufficiently transparent to be explained and audited. However, the explanation is of such complexity, that albeit transparent, would only be understood by an expert or the designer of that system. In one case the explanation for a given action is so simple that it is unnecessary. In the other the explanation is to complex that no lay person would be able to follow. Certainly much more work is required here in order to assess to what level and under which circumstances an explanation should be provided. It is always understood (although not always mentioned) that the explanation should be understood by the operator or user. Now that makes for an interesting challenge … Right?

As has been pointed out above, making a human trust a non-human agent is not only a matter of explainability assuming this explanation is understood. Any trust bond will have a utility or perceived value associated. The initiation of a trust bond may be faith based if no prior information is available. This initial phase often is associated with a degree of anxiety or fear of your trust is not fulfilled. There may be a high degree of dependability involved in the trust bond (e.g., autonomous driving) that adds to the anxiety. Only after prior experience or information becomes available will the importance of faith and anxiety around the assumed dependability diminish. The strength of the trust bond will increase. However, as the trust increase it also will also be increasingly sensitive to disappointment and perceived betrayal (also depending on the assigned utility to the bond). Too little work has been conducted understanding gender and cultural differences in the human-AI trust process. This is also true in general for any human-non-human trust relationships.

Some recent work indicates that anthropomorphizing (i.e., humanizing) the automation or AI-based agent appears to trigger neurochemical processes important in human-human trust bonds. See some pretty cool experiments towards the importance of anthropomorphizing automation agent by Visser et al (Visser, Monfort, Goodyear, Lu, O’Hara, Lee , Parasuraman & Krueger 2017) in their paper “A little anthropomorphism goes a log way: Effects of Oxytocin on Trust, Compliance, and Team Performance with Augmented Agents”. The question here is how far we can take humanizing AI. Will there be an uncanny valley effect at some point. Moreover, not all AI-functions should be humanized (that would be scary if even possible). Context clearly matters here. Lots of questions, still many answers outstanding and thus lots of cool research to be pursued.

ADDITIONAL SOURCES OF WISDOM.

Balfe N., Sharples S., and Wilson J.R., (2018). “Understanding is key: An analysis of factors pertaining to trust in a real-world automation system”. Human Factors, 60, pp. 477-495. Due to its recent publication you will find a good up to date account (as well as bibliography) on the state of art of human-automation trust research. This work establishes a strong connection between trust in and the understanding of automation.

Barret L.F., (2017). “How emotions are made: the secret life of the brain“. Houghton Mifflin Harcourt.

Baumgarten T., Fischbacher U., Feierabend A., Lutz K., and Fehr E., (2009). “The Neural Circuitry of a Broken Promise”. Neuron, 64, pp. 756 – 770.

Bergland, C., (2015). “The Neuroscience of Trust”, http://www.psychologytoday.com, August.

Choleris, E., Pfaff, D. and Kavaliers, M., (2013). “Oxytocin, vasopressin, and related peptides in the regulation of behavior”. Cambridge: Cambridge University Press.

Dawes R.M., (1979), “The robust beauty of improper linear models in decision making”, American Psychologist 571, pp.

Denson T.F., O’Dean S.M., Blake K.R., and Beames J.R., (2018). “Aggression in women: behavior, brain and hormones“. Frontiers in Behavioral Neuroscience, 12, pp. 1-20 (Article-81).

Dietvorst B.J., Simonojs J.P. and Massey C., (2014). “Algorithm Aversion: people erroneously avoid algorithms after seeing them err.”, Journal of Experimental Psychology: General, pp. . A study on the wide spread Algorithm Aversion, i.e., human expectations towards machines are substantially higher than to fellow humans. This results in a irrational aversion of machine based recommendations versus human-based recommendation. Even though algorithmic based forecasts are on average better to much better than human based equivalent in apples by apples comparisons.

Doshi-Velez F. and Korz M., (2017). “Accountability of AI under the law: the role of explanation“. Harvard Public Law, 18, pp. 1-15. Focus on the right to an explanation and what that might mean. Also very relevant to the European GDPR Article 22. Do note that whether Article 22, and Articles 13-15 as well, really does grant a user the right to an explanation is a matter of debate as pointed out by Wachter et al (2017).

Fischer K., (2018). “When transparency does not mean explainable”. Workshop on Explainable Robotic Systems (Chicago, March).

Frey C.B. and Osborne M.A., (2013). “The future of employment: how susceptible are jobs to computerization?“. Technology Forecasting and Social Change, 114, pp. 254-280.

Hawksworth J. and Berriman R., (2018). “Will robots really steal our jobs? An international analysis of the potential long term impact of automation“. PwC report.

Hiltbrand T., (2018), “3 Signs of a Good AI Model”. http://www.tdwi.org, November.

Ito J., (2018). “The limits to explainability“, Wired (January).

Kosfeld M., Heinrichs M., Zak P.J., Fischbacher U., and Fehr E., (2005). “Oxytocin increases trust in humans”. Nature, 435, pp. 673-676.

Kramer R.M., (2009), “Rethinking Trust”. Harvard Business Review, June.

Larsen, K., (2017). “On the acceptance of artificial intelligence in corporate decision making a survey“. http://www.aistrategyblog.com.

Law S., (2010), “Dad. too. get hormone boost while caring for baby”, http://www.livescience.com, October. Oxytocin is not only women for women breastfeeding. Research shows that men too have increased levels of oxytocin coinciding with child caring, physical contact and their spouse (and mother to their child).

Madhavan P. and Wiegmann D.A., (2007), “Similarities and differences between human-human and human-automation trust: an integrative review”. Theoretical Issues in Ergonomics Science, 8, pp. 277-301. (unfortunately behind paywall).

Meehl, P. E., (1954). “Clinical versus statistical prediction: A theoretical analysis and review of the literature“. University of Minnesota, pp. 1-161. Algorithmic versus human performance up-to the 50s is very well accounted for with Paul Meehl research work and his seminal book. It is clear that many of the topics we discuss today are not new.

Mori, M., MacDorman, K. and Kageki, N. (2012). “The Uncanny Valley [From the Field]“. IEEE Robotics & Automation Magazine, 19(2), pp. 98-100.

Nave G., Camerer C., and McCullough M., (2015), “Does Oxytocin Increase Trust in Humans? A Critical Review of Research”. Perspectives on Psychological Science, 10, pp. 772-789. Critical review of research into Oxytocin key role in social attachment including its effect of increased trust in human individuals with increased levels (above normal) of Oxytocin. Nave et al concludes that current results does not provide sufficient robust evidence that trust is associated with Oxytocin or even caused by it.

Rao A. and Cameron E., (2018), “The Future of Artificial Intelligence Depends on Trust”. Strategy+Business, July. Making the case for transparent, explainable and auditable AIs and why those concepts are important for the development of trust between humans and AI.

Rempel J.K., Holmes, J.G. and Zanna M.P., (1985), “Trust in close relationships”. Journal of Personality and Social Psychology, 49, pp. 95–112. (unfortunately behind paywall, however it is imo a super good account for trust in human to human relations).

Sapolsky R.M., (2017). “Behave: The Biology of Humans at Our Best and Worst”. Penguin Press. Robert Sapolsky addresses trust across his epic book from a neurobiological and behavioral perspective. Yes, you should read it!

Sheridan T.B. and Parasuraman R., (2005), “Chapter 2: Human-Automation Interaction”. Reviews of Human Factors and Ergonomics, 1, pp. 89 – 129. This is a really authoritative account for human interaction with automation as we find it in complex large-scale systems (e.g., aircrafts, aircraft control, manufacturing robotics-intensive plants, modern communications networks, modern power plants, chemical industries and infrastructure, modern as well as autonomous vehicles & drones, etc…).

Simpson J.A., (2007), “Psychological Foundations of Trust”. Current Directions in Psychological Science, 16, pp. 264-268.

Visser, E.J.d., Monfort S.S., Goodyear K., Lu L., O’Hara M., Lee M.R., Parasuraman R., and Krueger F., (2017), “A little anthropomorphism goes a log way: Effects of Oxytocin on Trust, Compliance, and Team Performance with Augmented Agents”. The Journal of the Human Factors and Ergonomics Society, 59, pp. 116-133.

Wachter S., Mittelstad B., and Floridi L., (2017). “Why a right to explanation of automated decision-making does not exist in the General Data Protection Regulation“. International Data Privacy Law, pp. 1-47. Wachtel et al claims that Article 22 (or other articles for that matter) does not express that users of automated decision-making applications have a right to an explanation. If anything at most a user may have a right to information about the decision process. It for solved a puzzle as there is nowhere in Article 22 any mention of an explanation more of a right to opt out. Articles 13 to 15 (of GDPR) only offers limited information about the process of which a given decision has been made (e.g., 15 and 14 are maybe the strongest articles with respect to information provision).

Wachter S., Russel C., and Mittelstad B., (2018). “Counterfactual explanations without opening the black box: automated decisions and GDPR“. Harvard Journal of Law & Technologies, 31, pp. 1-52.

Whitbourne S.K., (2015), “Why betrayal hurts so much (and who seeks revenge)”. http://www.phychologytoday.com, April.

Wickens C.D. and Dixon S.R., (2007), “The benefit of imperfect diagnostic automation: a synthesis of the literature”. Theoretical Issues in Ergonomics Science, 8, pp. 201-212.(unfortunately behind paywall). Wickens & Dixon has reviewed data from 20 studies upon which they have derived that a reliability cross-over point of about 70%. Below 70% no automation was regarded better than automation. Only above 70% reliability did automation bring positive cost-benefit returns.

Yao S., Zhao W., Cheng R., Geng Y., Luo L., and Kendrick K.M., (2014). “Oxytocin makes females, but not males, less forgiving following betrayal of trust“. International Journal of Neuropsychopharmacology, 17, pp. 1785-1792.

Zak P.J., (2017), “The Neuroscience of Trust”. Harvard Business Review, January-February.

2018 Edelman Trust Barometer (Global Report).

ACKNOWLEDGEMENT.

I rely on many for inspiration, discussions and insights. Any mistakes made are my own. In particular I would like to thank Liraz Margalit and  Minoo Abedi for many useful suggestions and great inspirational discussions around the topic of trust. I also greatly acknowledge my wife Eva Varadi for her support, patience and understanding during the creative process of writing this Blog.

Do we Humans trust AIs?

AI … IT IS HERE, IT IS THERE, IT IS EVERYWHERE.

I was late to a dinner appointment, arranged by x.ai, at Caviar and Bull (booked by my human friend David). Siri had already indicated that I would be late (yes it had also warned me repeatedly it was time to leave the office for me to be on time) and Waze (i.e., the world’s largest community-based traffic & navigation app) was trying to guide me through a busy Budapest city center. Stuck in traffic … sighhh … but then the traffic moves … I press on the speeder … and … my car breaks (with a vengeance) at the same moment my brain realizes that the car in front of me had not moved and I was about to hit it. My car had just saved me from a crash. And from being even later for my appointment of what would turn out to be an absolutely excellent dinner with great Hungarian reds and white wines recommended by Vivino (i.e., based on my wine history & preferences, my friends’ preferences and of course the menu). In the meantime, my scheduler had notified my friend that I would be a bit late due to traffic (rather than the real reason of me being late leaving the office;-).

Most of the above are powered by AI (also indicated by the color red) or more accurately machine learning applications. Thus based on underlying machine learning algorithms and mathematical procedures applied to available personalized, social networks and other data.

In the cases above I am implicitly trusting whatever automation has “sneaked” into my daily life will make it move convenient and possibly even save others as well as myself from harm (when my own brain & physiology gets too distracted). Do I really appreciate that most of this convenience is based on algorithms monitoring my life (a narrow subset that is of my life) and continuously predicting what my next move might be in order to support me? No … increasingly I take the offered algorithmic convenience for granted (and the consequences of that is another interesting discussion for another time).

In everyday life, we frequently rely on AI-driven and augmented decisions … mathematical algorithms trained on our and others’ digital footprint and behaviors … to make our lives much more convenient and possibly much safer.

The interesting question is whether people in general are consciously aware of the degree of machine intelligence or algorithmic decision-making going on all around them? Is it implicit trust or simply ignorance at play?

Do we trust AI? Is AI trustworthy? Trustworthy? Do we trust AI more than our colleagues & peers? and so forth … and what does trust really mean in the context of AI and algorithmic convenience?

Some of these questions relating to corporate decision-making have in detail been described in the context of the corporate decision makers’ sentiment towards AI in my previous blog “On the acceptance of artificial intelligence in corporate decision making – a survey”.

human trust

TRUST – HUMAN VS AI.

Imagine that you have a critical decision to make at your work. Your team (i.e., your corporate tribe) of colleague experts recommends, based on their human experience, to choose Option C as the best path forward.

Would you trust your colleagues’ judgment and recommendation?

Yes! There is a pretty high likelihood that you actually would.

More than 50% of corporate decision-makers would frequently to always trust the recommendation (or decision) based on human expert judgment. More than 36% of corporate decision-makers would trust such a recommendation in about half the time (i.e., what I call the flip coin decision-making).

Now imagine you are having a corporate AI available to support your decision-making. It also provides the recommendation for Option C. Needles maybe to say, but nevertheless let’s just say it; the AI has of course been trained on all available & relevant data and roughly tested for accuracy (i.e., in a lot more rigorous way than we test our colleagues, experts, and superiors)

Beside Humans (Us) versus AI (Them), the recommendation and decisions to be made are of course same.

Would you trust the AI’s recommendation? Would you trust it as much as you do your team of colleagues and maybe even your superior?

Less than 13% of corporate decision-makers would frequently always trust a recommendation (or decision) based on AI judgment. Ca. 25% of the decision makers would trust an AI-based decision about half the time.

Around 20% of decision-makers would never trust an AI-based decision. Less than 45% would do so only infrequently.

human vs ai - trust in decisions

Based on a total of 426 surveyed respondents of which 214 were offered Question A and 212 was offered Question B. Respondents are significantly more trusting towards decisions or recommendations made by a fellow human expert or superior than if a decision or recommendation would be made by an AI. No qualifications were provided for success or failure rate.

It is quite clear that we regard a decision or recommendation as based on AI, rather than a fellow human, with substantially less trust.

Humans don’t trust decisions made by AIs. At least when it is pointed out that a decision is AI-based. Surprisingly, given much evidence to the contrary, humans trust humans, at least the ones in our own tribe (e.g., colleagues, fellow experts, superiors, etc..).

Dietvorst and coworkers refer to this human aversion towards non-human or algorithmic-based recommendations or forecasts as algorithmic aversion. It refers to situations where human decision-makers or forecasters deliberately avoid statistical algorithms in their decision or forecasting process.

A more “modern” word for this might be AI aversion rather than algorithm aversion. However, it describes very much the same phenomena.

trust and mistrust

Okay, okay … But the above question of trust did not qualify the decision-making track record of the human versus the AI. Thus respondents could have very different ideas or expectations about the success or error rates of humans and AIs respectively.

What if the fellow human expert (or superior) as well as the AI is known to have a success rate that is better than 70%. Thus more than 7 out of 10 decisions are in retrospect deemed successful (ignoring whatever that might really mean). By the same token, it also means that the error rate is 30% or less … or that 3 (or less) out of 10 decisions are deemed unsuccessful.

human vs ai - trust in decisions w 70% success rate

Based on a total of 426 surveyed respondents of which 206 were offered Question A and 220 were offered Question B. For both Human Experts (or Superior) and AI, a decision-making success rate of 70% (i.e., 7 out of 10) should be assumed. Despite the identical success rate, respondents remain significantly more trusting towards decisions made by a fellow human expert (or superior) than if a decision would be made by an AI.

In a like-for like-decision making success rate, human experts or superiors are hugely preferred over a decision-making AI.

A bit more than 50% of the corporate decision makers would frequently or always trust a fellow human expert recommendation or decision. Less than 20% would frequently or always trust a decision made by an AI with the same success rate as the human expert.

Thus, Humans trust Humans and not so much AIs. Even if the specified decision-making success rate is identical. It should be noted that trust in a human decision or recommendation relates to fellow human experts or superiors … thus trust towards colleagues or individuals that are part of the same corporate structure.

The result of trust in the human expert or superior with a 70% success rate is quite similar to the previous result without a specified success rate

human vs ai - trust in human decisions

Based on a total of 426 surveyed respondents of which 214 were offered Question A without success rate qualification and 223 were offered Question A with a 70% success rate stipulated. As observed in this chart, and confirmed by the statistical analysis, there is no significant difference in the trust in a decision made by a human expert (or superior) whether a success rate of 70% has been stipulated or no qualification had been given.

This might indicate that our human default expectations towards a human expert or superior’s recommendation or decision are around the 70% success rate.

However, for the AI-based recommendation or decision, respondents do provide a statistically different trust picture depending on whether a success rate of 70% or not has been specified. The mean sentiment increases with almost 15% by specifying that the AI has a 70% success rate. This is also very visible from the respondent data shown in the below chart;

human vs ai - trust in ai decisions

Based on a total of 426 surveyed respondents of which 212 were offered Question B without success rate qualification and 203 were offered a Question B with a 70% success rate assumed. As observed in this chart, and confirmed by the statistical analysis, there is a substantial increase in trust of the AI-based decision where the success rate of 70% had been stipulated compared to the question where no success rate was provided.

Respondents that would never or infrequently trust an AI-based decision are almost 20% lower when considering a 70% success rate.

This might indicate that the human default perception of the quality of AI-based decisions or recommendations is far below the 70% success rate.

So do we as humans have higher expectations towards decisions, recommendations, or forecasts based on AI than the human expert equivalent?

human vs ai - expectations towards decision quality

Based on a total of 426 surveyed respondents of which 206 were offered Question A and 220 were offered Question B. No statistical difference in the expectations towards the quality of decisions where found between human expert (or superior) and that of AI-based ones.

This survey indicates that there is no apparent statistically significant difference in what quality we expect from a human expert compared to that of an AI. The average expectation towards the quality is that less than 2 out of 10 decisions could turn out wrong (or be unsuccessful). Thus, a failure rate of 20% or less. Similar to a success rate of 80% or better.

It is well known that depending on whether a question is posed or framed in a positive way or negative can greatly affect how people will decide. Even if the positive and negative formulations are mathematically identical.

An example; you are with the doctor and he recommends an operation for your very poor hearing. Your doctor has two options when he informs you of the operation’s odds of success (of course he might also choose not to provide that information altogether if not asked;-); Frame A. There is a 90% chance of success and you will be hearing normally again on the operated ear, Frame B. There is a 10% chance of failure and you will become completely deaf on the operated ear. Note that the success rate of 90% also implies an error rate of 10%. One may argue that the two are mathematically identical. In general, many more would choose to have an operation when presented with Frame A, i.e., a 90% success rate, than if confronted with Frame B, i.e., a 10% failure rate. Tversky & Kahneman identified this as the framing effect, where people react differently to a given choice depending on how such a choice is presented (i.e., success vs failure). As Kahneman & Tversky showed, the loss is felt to be more significant than the equivalent gain.

When it comes to an AI-driven decision would you trust it differently depending on whether I present you the AI’s success rate or its error rate? (i.e., the obvious answer is of course yes … but to what degree?)

ai trust - success vs failure rate

Based on a total of 426 surveyed respondents of which 233 were offered Question A (i.e., framed as decision success rate) and 193 Question B (i.e., framed as decision error rate). As expected from framing bias and prospect theory more respondents would trust the AI when presented with the AI’s success rate (i.e., better than 95%) compared to its error rate (i.e., less than 5 out of 100)

When soliciting support for AI augmentation a positive frame of its performance is (unsurprisingly) much better than the mathematically equivalent negative frame, i.e., success rate versus failure or error rate.

Human cognitive processes and biases treat losses or failures very differently from successes or gains. Even if the two frames are identical in terms of real-world impact. More on this later when we get into some cool studies on our human brain chemistry, human behavior, and Tversky & Kahneman’s wonderful prospect theory (from before we realized that oxytocin and other neuropeptides would be really cool).

HUMANS TRUST HUMANS.

Trust is the assured reliance on the character, ability, or truth of someone or something. Trust is something one gives as opposed to trustworthiness which is someone or something other being worthy of an individual or group’s trust.

The degree to which people trust each other is highly culturally determined with various degrees of penalties associated with breaking trust. Trust is also neurobiological determined and of course context dependent.

As mentioned by Paul J. Zak in his Harvard Business Review article “The Neuroscience of Trust” ; “Compared to people in low-trust companies, people in high-trust companies report: 74% less stress, 107% more energy at work, 50% higher productivity, 13% fewer sick days, 76% more engagement, 29% more satisfaction with their lives, 40% less burnout” … Trust is clearly important for corporate growth and the individuals’ wellbeing in a corporate setting (and I suspect anywhere really). Much of this is described mathematically (and I would argue beautifully) in Paul Zak’s seminal paper “Trust & Growth” relating differences in the degree of trust as it relates to different social, legal, and economic environments.

People trust people. It is also quite clear from numerous studies that people don’t trust that many non-people (e.g., things or non-biological agents such as mathematical algorithms or AI-based),.. okay okay you might say … but why?

While 42 is in general a good answer … here the answer is slightly simpler … Oxytocin (not to be confused with an oxymoron). Okay okay … what is that Oxytocin and what do they have to do with trusting or not trusting AI (that is the answer). Well … if you have read Robert Sapolsky’s brilliant account of our behavior at our best and worst (i.e., “Behave: the biology of humans at our worst and best” by Robert Sapolsky) you might know enough (and even more about those nasty glucocorticoids. And if you hadn’t had enough of those please do read “Why Zebras don’t get ulcers” also by Sapolsky, you might even be able to spell it in the end).

Oxytocin is our friend when it comes to warm and cozy feelings towards each other (apart from fairly being essential for inducing labor and lactation). Particularly when “each other” is part of our Team, our Partner, our kids, and even our Dog. It is a hormone of the peptide type (i.e., it is relatively small and consists of amino acids) and is used by neurons to communicate with each other. They pretty much influence how signals are processed by our brain and how our body reacts to external stimuli.

The higher the level of oxytocin, the more you are primed to trust your team, your stock broker, your partner (and your dog), feeling closer to your wife and your newly born babies. The more you hug, kiss, and shake hands, have sex, and walk your dog, the more Oxytocin will be rushing through your body and the more trusting you will become towards your social circles. “Usness” is great for oxytocin release (as well as a couple of other neuropeptides with a crack for making us feel better with one another … within the confines of “Usness” … oh yeah and we have some serious gender biases there as well). Particularly when “Them” are around. Social interactions are important for the oxytocin kick.

The extra bonus effect of increased oxytocin is that it appears to dampen the brain’s “freaking out” center’s (i.e., amygdala) reactivity to possible threats (real or otherwise). At least within the context of “Usness” and non-existential threats.

HUMANS DON’T TRUST AI (as much as Humans).

Oxytocin (i.e., changes in level) appears mainly to be stimulated or triggered by interaction with other humans (& dogs). When the human (or dog) interaction is taken out of the interaction “game”, for example, replaced by an electronic or mechanical interface (e.g., computer interface, bot interaction, machine, etc..) , trust is not enhanced by oxytocin levels. This has been well summarized by Mauricio Delgado in his “To trust or not to trust: ask oxytocin” Scientific American, as well as in the groundbreaking work of Paul J. Zak and co-workers (see “Oxytocin increases trust in Humans” from Nature, 2005) and likewise impressive work of Thomas Baumgartner et al. (“Oxytocin shapes the neural circuitry of trust and trust adaptations in humans” from Neuron, 2008).

Thomas Baumgartner and coworkers (similar setup to other works in this field) administrated either a placebo or oxytocin intranasal spray to test subjects prior to the experimental games. Two types of games were played; (a) so-called trust game with human partner interactions (i.e., human-human game) where the test subject invest an amount of money to a 3rd party (e.g., stock broker) that will invest the money and return the reward and (b) a so-called risk game of which the outcome would be machine determined by a random generator (i.e., human-machine game). The games are played over 12 rounds with result feedback to the test subject, allowing for a change in trust in the subsequent round (i.e., the player can reduce the invested money (less trust), increase (higher trust) or keep it constant (keep trust level)). Baumgartner et al found that test subjects playing the trust game (human-human game), and who received the oxytocin “sniff”, remained trusting in throughout rounds of the game, even when they had no rational (economical) reason to remain trusting. The oxytocin subjects trust behavior was found to be substantially higher compared to test subjects playing the same game having received the placebo. In the risk game (human-machine) no substantial differences were observed between oxytocin and placebo subjects which in both cases kept their trust level almost constant. While the experiments conducted are fascinating and possibly elucidating towards the effects of oxytocin and social interactions, I cannot help being somewhat uncertain whether the framing of Trust vs Risk and the subtle game structure differences (i.e., trusting human experts that supposedly know what he is doing vs lottery a game of chance) could skew the results. Thus, rather than telling us whether humans trust humans more than machines or algorithms (particularly the random generator kind of which trust is somewhat of an oxymoron), it tells us more about how elevated levels of oxytocin make a human-less sensitive to mistrust or angst for a fellow human being (that might take advantage of that trust).

It would have been a much more interesting game (imo) of both had been called a Trust Game (or Risk Game for that matter as this is obviously what it is). One game with a third party investing in the test subjects’ transfer. Thus similar to Baumgartner’s Trust Game setup. And another game where the third party is an algorithmic “stock broker” with at least the same success rate as the first game’s 3rd party human. This would have avoided the framing bias (trust vs risk) and the structural differences in the game.

Unfortunately, we are not that much closer to a great explanation for why humans appear to trust humans more than algorithms. Still pretty much guessing.

And no I did not hand out cute oxytocin (and of course placebo) nasal spays to the surveyed respondents. Neither did I check for whether respondents had been doing a lot of hugging or other close-quarter social network activities which would have boosted the oxytocin levels. This will be for a follow-up study.

intranasal oxytocin sprays

In Baumgartner’s experiment, subjects got 3 puffs of Oxytocin or Placebo per nostril for each of 4 IUs (i.e., 24 IUs or ml). Note: the bottle above is just a random sample of a nostril oxytocin spay.

A guess towards a possible explanation for humans being statistically significantly less trusting towards algorithms (algorithmic aversion), AI (AI aversion), and autonomous electronic-mechanistic interfaces in general, might be that our brains have not been primed to regard such as part of “Usness”. In other words, there is a very big difference between trusting colleagues or peers (even if some are superiors) who are part of your corporate “tribe” (e.g., team, unit, group, etc…) compared to an alien entity such as an AI or an algorithm could easily be construed.

So the reasons why humans trust humans and algorithms and AI is still somewhat reclusive although the signals are possibly there.

Based on many everyday machine learning or algorithmic applications leapfrogging our level of convenience already today … Maybe part of the “secret” is to make AI-based services and augmentation part of the everyday.

The human lack of trust in AI, or the prevalence of algorithms aversion in general as described in several articles by Berkeley Dietvorst, in a corporate sense and setting is nevertheless a very big challenge for any ideas of a mathematical corporation where mathematical algorithms are permeating all data-driven decision processes.

GOOD & RELATED READS.

ACKNOWLEDGEMENT.

I greatly acknowledge my wife Eva Varadi for her support, patience, and understanding during the creative process of creating this Blog. Without her support, I really would not be able to do this or it would take long past my expiration date to finish.

SURVEYS.

Unless otherwise specified the results presented here comes from a recent surveymonkey.com survey that was conducted between November 11th, 2017 and November 21st 2017. The Survey took on average 2 minutes and 35 seconds to complete.

The data contains 2 main survey collector groups;

  1. Survey Monkey paid collector group run between November 11th and 14th 2017 with 352 completed responses from USA. Approximately 45% were Females and 55 males in the surveyed sample with an age distribution between 18 and 75 years of age. The average age is 48.8. The specified minimum income level was set to $75 thousand or about 27% higher than the median US real household income level in 2016. The average household income level in this survey is approx. 125 thousand annually. Ca. 90% or 316 out of the 352 respondents have heard of Artificial Intelligence (AI) previously. For AI-relevant questions, only 316 were used. A surveyed respondent that had not previously heard of AI (36 out of 252) was not considered. More than 70% of the respondents had a 4-year college or graduate-level degree. About 70% of the respondents were married and 28% had children under the age of 18. Moreover, ca. 14% currently had no employment.
  2. Social Media (e.g., Facebook, LinkedIn, Twitter, …) collector group run between November 11th and 21st 2017, and completed in total of 115 responses primarily from the telecom & media industry mainly from Europe. Gender distribution comprised around 38% Female and 62% Male. The average age for this sample is 41.2. No income data is available for this group. About 96% (110) have heard of Artificial Intelligence. For AI-related questions, only respondents that have confirmed they have heard about AI have been considered. Ca. 77% of the respondents have a 4-year college or graduate-level degree. 55% of the surveyed sample are married and a bit more than 50% of this surveyed group have children under 18. Less than 2% of the respondents were currently not employed.

It should be emphasized that SurveyMonkey was a paid survey with 2.35 euros per response, totaling 1,045 euros for 350 responses. Each respondent completed 18 questions. Age balancing was chosen to be basic and the gender balancing census.

Expectations towards & Acceptance of Artificial Intelligence in Corporate Decision Makings.

A SURVEY PRIMER.

I am currently conducting some research into corporate decision making, as referenced to the individual corporate decision maker, and the extent and perceived quality of data-driven decisions in the corporate decision making process.

In this (initial) research, it is of particular interest to understand the extend of corporate data-driven decision making. The initial part of the survey focuses on (1) type of corporate decisions made, (2) the availability of data used in the decision making, (3) the structure of such data, (4) the quality of such available data and so forth.

The second part of the Survey attempts to gauge human expectations towards and acceptance of artificial intelligence (A.I.) in corporate decision making as it relates to the individual decision maker and the overall corporate decision making process.

The (bold blue text) link below takes you to the Survey with 24 questions which should take less than 4 minutes (current average is 3 minutes 31 seconds);

“Perceived quality and acceptance of Human & Artificial Intelligence Augmentation in Corporate Decision Making.”

The survey results will be published in an essay I am currently writing on “Corporate Decision Making – The neuroscience of human decisions and the role that Artificial Intelligence may play” (working title!;-). Some of the thoughts and analysis will also appear here on this Blog … so stay tuned.

The impact of A.I. is widely discussed and reasonably understood in the context of consumerism, product development and the harder science (i.e., at least the “hows”, maybe not always the “whys”).

Little research work has been done on how Artificial Intelligence may shape businesses and their corporate decision making processes. Certainly, very little is known about the sentiment of management and executives towards A.I. in context of decision making and the possibility of augmenting such with A.I.-based insights. The impact of A.I. augmentation on the individual corporate decision maker, as well as for the business in its totality, is likely to be transformative.

So far I have collected survey data from 550+ executives and managers.

If you have taken the survey then very much appreciated and thanks (please don’t take it again;-). If you have not yet, please click the above link … it should not take more than maximum 4 minutes of your life.

I expect to publish the first results of this Survey by early October.

Thanks!