GPT-5.6 - Hackdot

Re:GPT-5.6 by arjie on Thursday July 09, 2026 @01:53PM (#48849889)

They do, and I want to encourage them to do so because they think through talking. What I don’t want to do is spend time reading all that.

We will probably just get reader-side affordances for this like auto-folded justification and introduction sections and so on.

Doubtless some chat interface will add this the way they’ve added reasoning folding.

[ Parent | on HN ]

Re:GPT-5.6 by bcrosby95 on Thursday July 09, 2026 @02:04PM (#48850049)

Thinking models think through talking, don't reveal that talking, then answer by again thinking through talking. It's kinda funny in a way.

[ Parent | on HN ]

Re:GPT-5.6 by mdgld on Thursday July 09, 2026 @07:37PM (#48853887)

I always expose reasoning traces. How else can you seriously debug?

[ Parent | on HN ]

Re:GPT-5.6 by girvo on Friday July 10, 2026 @03:46AM (#48856969)

The closed models aren't giving you the real thinking traces, though.

[ Parent | on HN ]

Re:GPT-5.6 by joquarky on Friday July 10, 2026 @05:47AM (#48857856)

Those traces are just summaries of the reasoning.

[ Parent | on HN ]

Re:GPT-5.6 by alfiedotwtf on Saturday July 11, 2026 @05:45AM (#48870430)

It’s wild the people don’t want to see the thinking

[ Parent | on HN ]