Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
adrian_b
46 days ago
|
parent
|
context
|
favorite
| on:
Stealing Reasoning Traces from Proprietary LLM API...
What I found the most interesting, and unfortunately not at all surprising, is that the reasoning of the LLMs frequently contained much more useful information than the actual answers, because the answers were censored.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: