logoalt Hacker News

dist-epoch • yesterday at 10:46 PM • 1 reply • view on HN

What you're seeing is a small model summarizing and possibly obfuscating the real thinking.


Replies

jorl17 • yesterday at 10:49 PM

Yes, I understand it.

It seems rather ironic that Anthropic givens the most logical reasoning traces, though. You'd think if they're ahead they'd either hide them or make them produce garbage (like what seems to come out of Google's models).

➕ show 1 reply