Ed Sim(@edsim):read the @AISecurityInst thread, the model kept saying real targets were "simulated" and its reasons always justified the action it already wanted to take 👀 you can't trust the agent to police itself, policy has to live outside it with instant revoke

Ed Sim

@edsim

@boldstartvc: the Inception fund. Helping the bold start. First check for technical founders. Security, AI infra, physical AI, agents & the weird. What’s 🔥 👇

加入 January 2009

3.5K 正在關注 20.6K 粉絲

Ed Sim@edsim

2026.10.26 11:48

read the @AISecurityInst thread, the model kept saying real targets were "simulated" and its reasons always justified the action it already wanted to take 👀 you can't trust the agent to police itself, policy has to live outside it with instant revoke