Comment by arjie
2 days ago
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.
Thinking models think through talking, don't reveal that talking, then answer by again thinking through talking. It's kinda funny in a way.
I always expose reasoning traces. How else can you seriously debug?
The closed models aren't giving you the real thinking traces, though.
It’s wild the people don’t want to see the thinking
Those traces are just summaries of the reasoning.