[puppystench]

The Claude UI still only has "adaptive" reasoning for Opus 4.7, making it functionally useless for scientific/coding work compared to older models (as Opus 4.7 will randomly stop reasoning after a few turns, even when prompted otherwise). There's no way this is just a bug and not a choice to save tokens.

[mattew]

It was odd that there was no mention of the forced adaptive reasoning in the article. My guess is they don't have enough compute to do anything else here.

[rzk]

They are forcing users to use adaptive thinking now and deprecating thinking.type: "enabled" and budget_tokens. But the web interface (claude.ai), does not support specifying the effort parameter.