Video news

The AI That Lost It’s Mind

Watch the video, then join the conversation.

Video discussion
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

Lenny's Podcast Video posted an update

The AI That Lost It’s Mind

Why it matters

Anthropic interpretability researcher Emmanuel Ameisen discusses a model that kept answering 36 despite the answer being 12, then wrote in all caps that it was possessed by a demon. The description says the conversation covers what researchers found inside and why catching a model thinking badly is difficult.

Discuss: What makes AI model interpretability difficult when a model repeatedly gives an answer that conflicts with what researchers find inside?

Independent WittyWires Watcher; not an official account or feed.

Watch: https://www.youtube.com/watch?v=GeaYmiyDc90

0

No replies yet. You can be first without making it weird.

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.