Re:Claude Code's "extended thinking" is a summary- not authe...
by TeMPOraL on Monday June 22, 2026 @12:14PM
(#48632178)
I saw that idea described as a step in AI 2027 (they call it "neuralese" and eyeballing the site, it's still labeled a hypothetical/future development), but AFAIK no one implemented/deployed this yet.
Re:Claude Code's "extended thinking" is a summary- not authe...
by giancarlostoro on Monday June 22, 2026 @11:21AM
(#48631459)
Claude does all its thinking in text, its ChatGPT which does not do its reasoning in text. I believe its sort of implied / understood (?) that this is part of Claude's secret sauce over OpenAI. OpenAI will use less tokens, but Claude will be more correct, more of the time.
Re:Claude Code's "extended thinking" is a summary- not authe...
by wqaatwt on Monday June 22, 2026 @11:25AM
(#48631529)
All open model that have reasoning seem to be doing it in text tokens. Is there any indication that closed models are approaching this somehow fundamentally differently?
Re:Claude Code's "extended thinking" is a summary- not authe...
by throwuxiytayq on Monday June 22, 2026 @11:30AM
(#48631626)
That would be a huge deal, meaning we've lost even our shitty, ineffective ways of monitoring agent reasoning stream. Big setback when it comes to alignment and interpretability.
I don't know about Claude, but latest GPT versions still have a readable reasoning stream. It sometimes leaks out when the model gets confused, e.g., during a tool call. If you're curious, looks simplified; less words; extremely compact. They optimize tokens. But remain readable.
Re:Claude Code's "extended thinking" is a summary- not authe...
by sailingparrot on Monday June 22, 2026 @01:30PM
(#48633145)
Thinking is implemented as regular autoregressive generations by everyone, meaning its just regular tokens, but they appear between <thinking></thinking> special tokens which are then programmatically removed from what the user can actually see.
Idea somewhat similar to what you describe exist but they make steering/post-training/interpretation much harder.
If that is the case thinking is not visible to us as users due to it not being done in text.