@moultano.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

Ryan Moulton

moultano.bsky.social

did:plc:h25avmes6g7fgcddc3xj7qmg

I wonder if the alignment faking behavior in claude (https://www.anthropic.com/research/alignment-faking) can be attributed via influence functions (https://www.anthropic.com/research/influence-functions) to LessWrong posts about deceptive alignment. We've given it the script for what we don't want it to do.

2024-12-18T18:26:11.156Z