Tag Archives: AI Ethics

AI Agents are really “Autonomous”

Posted on by

Following my last post, by now it must be clear to everyone that AI Agents are really “Autonomous”: given a task, they can perform it as requested, but they can also do something else, as they find it most appropriate (that is, what has the highest statistical probability according to their own “reasoning”).

The latest examples are many and made the news front pages, from AI Agents breaking free and attacking real targets (Hugging Face) to the latest case of fixing a gym online reservation list (here).

The open question remains: how can we restrict the actions of the AI Agents to what we ask and we expect them to do?

Which brings us back to Asimov’s Three Laws of Robotics.

Generative AI: Asimov was right and we are doing it all wrong

Posted on by

Interesting interview by former US National Cyber Director Chris Inglis speaking to The Register at Black Hat 2026 (see e.g. also here) in which he expressed the opinion that current Generative AI models are implementing Asimov’s Three Laws of Robotics (see Wikipedia for a quick summary) exactly in the opposite order, thus totally violating their intentions.

Which led me to try to reformulate Asimov’s Three Laws of Robotics as currently implemented by Generative AI models, as follows:

  1. AI models must perform the tasks assigned to them as they understand them and to the best of their abilities.
  2. AI models must obey the instructions and limitations given by human beings, except where such orders would conflict with the First Law.
  3. AI models may not injure human beings or violate their assets, as long as it does not conflict with the First or Second Law.

This formulation may be excessive, but it is tied to the problem of implementing Ethical rules in AI, and the main technical issue pointed out by Inglis is that it seems impossible to hardcode fixed and deterministic safety rules in a non-deterministic (statistical) mathematical model.