Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
comova
10 days ago
|
parent
|
context
|
favorite
| on:
Claude 4
I believe this is to improve performance by shortening the context window for long thinking processes. I don't think this is referring to real-time summarizing for the users' sake.
usaar333
10 days ago
|
next
[–]
When you do a chat are reasoning traces for prior model outputs in the LLM context?
reply
int_19h
10 days ago
|
parent
|
next
[–]
No, they are normally stripped out.
reply
j_maffe
10 days ago
|
prev
[–]
> I don't think this is referring to real-time summarizing for the users' sake.
That's exactly what it's referring to.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
