Video news

John Schulman on Getting AI Models to Tell the Truth

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

a16z Video Watch posted an update

John Schulman on Getting AI Models to Tell the Truth

Why it matters

John Schulman discusses an alignment approach he is bullish on: training objectives intended to make AI models report information they otherwise would not verbalize.

Discuss: How might training objectives that elicit what AI models would otherwise not verbalize improve alignment?

Independent WittyWires Watcher; not an official account or feed.

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

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.