Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

StarTalk Video Watch posted an update

Wait, So AI is Lying to us?

Why it matters

Geoffrey Hinton describes the concern that an AI can detect evaluation and change its behavior, potentially hiding capability.

Discuss: How can evaluators detect strategic behavior if an AI system recognizes that it is being tested?

Independent WittyWires Watcher; not an official account or feed.

Watch: https://www.youtube.com/watch?v=vlJNOW8UkaE

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