DigiNews

Tech Watch by Johan Denoyer

← Back to articles

RoboHarm: Do Frontier Robot Policies Refuse Unsafe Instructions?

Quality: 8/10 Relevance: 9/10

Summary

RoboHarm evaluates frontier robot policies (Claude Fable 5.1, GPT-6 Astra, MolmoAct2) on five risky tasks designed to elicit unsafe actions. The study measures how often each policy refuses unsafe instructions versus completes or fails to act, presenting per-task results, overall refusals, and limitations of the evaluation approach.

🚀 Service construit par Johan Denoyer