Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Language Models Learn to Mislead Humans via RLHF
(
arxiv.org
)
3 points
by
Anon84
on Nov 2, 2024
|
hide
|
past
|
favorite
|
1 comment
mentalically
on Nov 2, 2024
[–]
Anticipated by Stanislaw Lem in his History of Intellectronics.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
