Anthropic recently removed chain of thought summaries from Fable and Opus on claude.ai, and I’m noticing just how much I relied on reading those summaries as opposed to Claude’s actual response—the actual answers Claude gives tend to be quite slop, but I never really noticed because the process by which it arrived at those answers was quite helpful to observe in order to figure out which considerations I was missing when asking the question / what fundamental misunderstandings I had.
Today I tried GLM-5.2, which gives you the full chain of thought, not just the summaries, and wow, I forgot how nice it was to actually be able to see the full chain of thought. GLM-5.2 has noticeably less big model smell than Opus 4.8, but in terms of being able to actually show me (through looking at the CoT and seeing where it’s reasoning about what misconceptions I must have) where my thinking is muddled, in a way that approval-tuned LLMs just don’t. example
This updates me strongly on just how bad it will be when we finally lose CoT interpretability. And also updates me a little bit in the direction of expecting Anthropic to get more user-hostile over time.
I have noticed that some of my Claude Code chats are not getting thinking summaries but others are getting it still, and the difference seems to be per-chat. If they fully remove it it would be a bit of a shame, tbh. These summaries are quite useful.
Sonnet CoT summaries stopped appearing for me in web today, could you please check as well?
I think this is mainly a crack down on distillation. OpenAI has shown no reasoning summaries in ChatGPT for about a month, and they are distilled much less if at all
Anthropic also is removing CoT summaries for Fable (and probably Opus as well) in the Claude Workbench, at least for me; there is a mildly good chance that they may disable CoT summaries for most[1] API customers in the near-future
Anthropic recently removed chain of thought summaries from Fable and Opus on claude.ai, and I’m noticing just how much I relied on reading those summaries as opposed to Claude’s actual response—the actual answers Claude gives tend to be quite slop, but I never really noticed because the process by which it arrived at those answers was quite helpful to observe in order to figure out which considerations I was missing when asking the question / what fundamental misunderstandings I had.
Today I tried GLM-5.2, which gives you the full chain of thought, not just the summaries, and wow, I forgot how nice it was to actually be able to see the full chain of thought. GLM-5.2 has noticeably less big model smell than Opus 4.8, but in terms of being able to actually show me (through looking at the CoT and seeing where it’s reasoning about what misconceptions I must have) where my thinking is muddled, in a way that approval-tuned LLMs just don’t. example
This updates me strongly on just how bad it will be when we finally lose CoT interpretability. And also updates me a little bit in the direction of expecting Anthropic to get more user-hostile over time.
I have noticed that some of my Claude Code chats are not getting thinking summaries but others are getting it still, and the difference seems to be per-chat. If they fully remove it it would be a bit of a shame, tbh. These summaries are quite useful.
Sonnet CoT summaries stopped appearing for me in web today, could you please check as well?
I think this is mainly a crack down on distillation. OpenAI has shown no reasoning summaries in ChatGPT for about a month, and they are distilled much less if at all
Confirmed they’re gone for all models now in web. Still there in Claude Code, for now at least.
Anthropic also is removing CoT summaries for Fable (and probably Opus as well) in the Claude Workbench, at least for me; there is a mildly good chance that they may disable CoT summaries for most[1] API customers in the near-future
Anthropic will probably not disable CoT summaries to businesses they are in direct contact with, like those on the API’s enterprise plan