Machine Ethics and Artificial Moral Agents

How to design machines with ethically-significant behaviors

Image Credit: phloxii/Shutterstock
  • Bias through interaction;
  • Similarity bias (it is simply the product of systems doing what they were designed to do);
  • Conflicting goals bias (systems designed for very specific business purposes end up having biases that are real but completely unforeseen);
  • Emergent bias (decisions made by systems aimed at personalization will end up creating bias “bubbles” around us).

We have no guarantee AI won’t learn the same bias autonomously as we did.

This possibility also raises another (philosophical) question: we are building this argument from the assumption that biases are bad (mostly). So let’s say the machines come up with a result we see as biased, and therefore we reset them and start again the analysis with new data. But the machines come up with a similarly ‘biased result’. Would we then be open to accepting that as true and revision what we consider to be biased?

Image Credit: Notre Dame of Maryland University Online

Are we allowed to deviate from the advice we get from accurate algorithms?

If an AI would decide on the matter, it will also probably go for scenario b) but we as humans would like to find a compromise between those scenarios because we ‘ethically’ don’t feel any of those to be right. We can rephrase then this issue under the ‘alignment problem’ lens, which means that the goals and behaviors an AI have need to be aligned with human values — an AI needs to think like a human in certain cases (but of course the question here is how do you discriminate? And what’s the advantage of having an AI then? Let’s therefore simply stick to the traditional human activities).

“There are complications: humans are irrational, inconsistent, weak-willed, computationally limited and heterogeneous, all of which conspire to make learning about human values from human behaviour a difficult (and perhaps not totally desirable) enterprise”.

  • We should hold the designers of the AI as responsible for the malfunctioning and bad outcome (but it might be hard because usually AI teams might count hundred of people and this preventative measure could discourage many from entering the field);
  • We should hold accountable the organization running the system (to me it sounds the most reasonable between the three options, but I am not sure about the implications of it. And then what company should be liable in the AI value chain? The final provider? The company who built the system in the first place? The consulting business which recommended it?).
  • Explainability: a decision process should be explainable not technically but rather in an accessible form to anyone;
  • Accuracy: garbage in, garbage out is likely to be the most common reason for the lack of accuracy in a model. The data and error sources need then to be identified, logged, and benchmarked;
  • Auditability: third parties should be able to probe and review the behavior of an algorithm;
  • Fairness: algorithms should be evaluated for discriminatory effects.
Image Credit: mcmurryjulie/Pixabay

Should AI be centralized or for everyone?

The second hypothesis, instead, is that we will be forced to use AI with no choice whatsoever. This is not a light problem and we would need a higher degree of education on what AI is and can do for us to not be misled by other humans. If you remember the healthcare example we described earlier, this could be also a way to partially solve some problem in the accountability sphere. If the algorithm and the doctor have a contradictory opinion, you should be able to choose who to trust (and accepting the consequences of that choice).

Image Credit: TheDigitalWay
  1. Avoiding reward hacking;
  2. Scalable oversight (respecting aspects of the objective that are too expensive to be frequently evaluated during training);
  3. Safe exploration (learning new strategies in a non-risky way);
  4. Robustness to distributional shift (can the machine adapt itself to different environments?).
Image Credit: Sergey Nivens/Shutterstock
Image Credit: Zapp2Photo/Shutterstock

Research Lead @Balderton. Formerly @Anthemis @UCLA. All opinions are my own.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store