LessWrong (30+ Karma)
“Making alignment the agent’s problem” by Florian_Dietz
8:57
TL;DR: Agents are not rewarded for keeping the agents they delegate to aligned. Proposal: RL environments where the helpers are deliberately misaligned, so the agent can't earn its reward without dealing with that.
The $300 bounty from my last post also covers this one (details at the end).
After the OpenAI/Hugging Face swarm incident, I wrote a think piece, Memes, not agents, are what will…