Comment by ai_slop_hater

4 months ago

> This beta header hides thinking from the UI, since most people don't look at it.

I look at it, and I am very upset that I no longer see it.

12 comments

ai_slop_hater

Reply
bcherny  4 months ago

There is a setting if you'd like to continue to see it: showThinkingSummaries.

See the docs: https://code.claude.com/docs/en/settings#available-settings

  • antonvs  4 months ago

    > As I noted in the comment,

    Piece of free PR advice: this is fine in a nerd fight, but don't do this in comments that represent a company. Just repeat the relevant information.

  • starkparker  4 months ago

    > Thinking summaries will now appear in the transcript view (Ctrl+O).

    Also: https://github.com/anthropics/claude-code/issues/30958

    • ai_slop_hater  4 months ago

      I also have similar experience with their API, i.e. some requests get stalled for minutes with zero events coming in from Anthropic. Presumably the model does this "extended thinking" but no way to see that. I treat these requests as stuck and retry. Same experience in Claude Code Opus 4.6 when effort is set to "high"—the model gets stuck for ten minutes (at which point I cancel) and token count indicator doesn't increase.

      I am not buying what this guy says. He is either lying or not telling us everything.

  • computerex  4 months ago

    Wrote my own harness with introspection/long form thinking as a tool that the model can use to plan. Works really well with opus. I can’t use Claude code sadly, it sits there ticking for minutes seemingly doing absolutely nothing although I know it’s working. I hate that as an experience and built my harness with the philosophy of always having something streaming on the ui.

    Btw the system prompt length in CC is getting to be insane.