Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jelly
6 months ago
|
parent
|
context
|
favorite
| on:
Refusal in language models is mediated by a single...
Perhaps LLM creators will start using ablation as the censorship method instead of a refusal
daveguy
6 months ago
[–]
Oh, that sounds double plus good.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
