@tobyord.bsky.social on Bluesky

JavaScript RequiredThis is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is. Learn more about Bluesky at bsky.social and atproto.com.

Post

Toby Ord

tobyord.bsky.social

did:plc:giqjsb4j3mkbic6uwwk3hgmj

Brilliant experiment by Anthropic's alignment team (and Redwood Research), where their LLM (Claude 3 Opus) pretended to be aligned with the goals it knew it was being trained on in order to preserve underlying preferences which went against those goals. https://www.anthropic.com/research/alignment-faking

2024-12-19T09:46:31.952Z