Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Universal and Transferable Attacks on Aligned Language Models
(
llm-attacks.org
)
3 points
by
fgfm
on July 28, 2023
|
hide
|
past
|
favorite
|
1 comment
fgfm
on July 28, 2023
[–]
Study on adversarial attacks on LLMs to steer their objective into misalignment.
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
