Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
bcrosby95
16 days ago
|
parent
|
context
|
favorite
| on:
GPT-5.6
Thinking models think through talking, don't reveal that talking, then answer by again thinking through talking. It's kinda funny in a way.
mdgld
16 days ago
[–]
I always expose reasoning traces. How else can you seriously debug?
girvo
16 days ago
|
parent
|
next
[–]
The closed models aren't giving you the real thinking traces, though.
alfiedotwtf
15 days ago
|
parent
|
prev
|
next
[–]
It’s wild the people don’t want to see the thinking
joquarky
16 days ago
|
parent
|
prev
[–]
Those traces are just summaries of the reasoning.
Consider applying for YC's Fall 2026 batch!
Applications
are open till July 27.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
