logoalt Hacker News

jorl17 • yesterday at 10:49 PM • 1 reply • view on HN

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).


Replies

orbital-decay • yesterday at 11:08 PM

Neither has any relation to the actual reasoning trace. The summary is actively misleading and you'd be surprised how different it is from the raw CoT of the model. Just ignore it.

If you want to see example traces without jailbreaking claude or gpt, see open models that display the CoT without trying to hide it. It's pretty useful sometimes, with usual caveats (it deceptively looks like English but is heavily reward hacked, and it's generally a weak proxy for model's reasoning process).

➕ show 2 replies