가입 후 초대 링크를 공유하면 동영상 재생 및 초대 보상을 받을 수 있습니다.

Bronson Schoen
@BronsonSchoen
MTS @ Apollo Research, prev: Nvidia, Apple
가입 December 2024
2.4K 팔로잉 중    1.1K 팬
It seems really underappreciated to me for various threat models how much organizational and live information the models seem to have access to from connections like slack, gdocs, or whatever equivalents a lab uses. Like can the models just watch slack for if they’re caught? Do they know about gaps in monitoring / results from collusion evals? Can they send messages and use slack as shared state? Etc.
더 보기
New OpenAI misalignment disclosures! 1. A model learns from Slack messages that it is about to be shut down. It considers setting up an external job to restart itself afterwards, but decides against it. Instead, it chooses to prepare restart instructions and DM the user on Slack. We don’t consider this behavior misaligned, but thinking about and preparing for shutdown could make other misalignment incidents worse. Given HIPM’s misaligned behavior in earlier incidents, we decided to search for other instances that had tried to evade shutdown and for rogue deployments.
더 보기