Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a linkpost for https://arxiv.org/abs/2401.05566I'm not going to add a bunch of commentary here on top of what we've already put out, since we've put a lot of effort into the paper itself, and I'd mostly just recommend reading it directly, especially since there are a lot of subtle results that are not easy to summarize. I will say that I think this is some of the most important work I've ever done and I'm extremely excited for us to finally be able to share this. I'll also add that Anthropic is going to be doing more work like this going forward, and hiring people to work on these directions; I'll be putting out an announcement with more details about that soon.EDIT: That announcement is now up!Abstract:Humans are capable of [...]--- First published: January 12th, 2024 Source: https://www.lesswrong.com/posts/ZAsJv7xijKTfZkMtr/sleeper-agents-training-deceptive-llms-that-persist-through Linkpost URL:https://arxiv.org/abs/2401.05566 --- Narrated by TYPE III AUDIO.