Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
stainablesteel
6 months ago
|
parent
|
context
|
favorite
| on:
Refusal in language models is mediated by a single...
if im understanding everything correctly the ablitation concept scouts the model for a similar concept to the "direction" described in this one, and it blocks it in order to "uncensor" the llm
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: