Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
salamo
8 months ago
|
parent
|
context
|
favorite
| on:
Golden Gate Claude
Absolutely. "Refusals" all seem to follow a similar direction in the LLM residual stream, so preventing the model from representing this direction prevents it from refusing.
https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in...
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in...