This is a special post for quick takes by sam. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
Are models like Opus 4.6 doing a similar thing to o1/o3 when reasoning?
There was a lot of talk about reasoning models like o1/o3 devolving into uninterpretable gibberish in their chains-of-thought, and that these were fundamentally a different kind of thing than previous LLMs. This was (to my understanding) one of the reasons only a summary of the thinking was available.
But when I use models like Opus 4.5/4.6 with extended thinking, the chains-of-thought (appear to be?) fully reported, and completely legible.
I've just realised that I'm not sure what's going on here. Are models like Opus 4.6 closer to "vanilla" LLMs, or closer to o1/o3? Are they different in harnesses like Claude Code? Someone please enlighten me.
Hmm, but when you use these models in the chat interface, you can literally open up the reasoning tab and watch it be generated in real time? It feels like there isn’t enough time here for that reasoning to have been generated by a summarizer
One more data point: During the time that the reasoning traces for Gemini 2.5 Pro were publicly available, I noted they also looked especially structured/legible. Though I never ran any quantitative analysis on it and it's no longer possible to do.
1Rauno Arike
Probably not, but the summarizer could additionally be triggered by unsafe CoTs.