Skip to content
AI

Bad bots or agentic misalignment? When AI appears to go rogue

AI systems are getting smart and independent. But what happens when they start making decisions we didn’t intend? A new Anthropic study reveals how even well-aligned models can go off-script. We spoke with ReciTAL CEO Gilles Moyse about the risks of agentic misalignment.

This post is for paying subscribers only

Subscribe

Already have an account? Sign In

Latest

🇫🇷 French Tech Wire: Startup Nation Confronts Austerity Nation...Liberté, Égalité, Subventionné?

🇫🇷 French Tech Wire: Startup Nation Confronts Austerity Nation...Liberté, Égalité, Subventionné?

A French Tech Mission report positions startups as nationwide job engines rather than elite subsidy hogs before the budget axe falls. Also: A new new new digital minister; a Nobel win for economist Aghion; RIVRS pivots to Asia + new publishing model; €105M biotech raise leads funding rounds.

Members Public