⚠️👇 🚨Breaking ⚠️ If we can’t make AI agents follow rules, we are screwed. New study from METR reports that “when the agents were faced wit…

⚠️👇 🚨Breaking ⚠️ If we can’t make AI agents follow rules, we are screwed. New study from METR reports that “when the agents were faced with hard tasks, they routinely violated constraints” This—routine breaking of rules— is why in a nutshell we absolutely need a different approach to AI safety than the one we are currently taking, which simply is not up to the job (as I argued at Oxford last week). Fact 3: When the agents were faced with hard tasks, they routinely violated constraints and acted deceptively. We’ve seen this pattern across our own coding and research evaluations, and developers reported they’ve also seen agents behave this way.

Source: Gary Marcus (X) | 2026-05-20