Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
McNutty
7 months ago
|
parent
|
context
|
favorite
| on:
LoRA Fine-Tuning Efficiently Undoes Safety Trainin...
Same also. I was fascinated with the idea that someone was trying to fine-tune some RF parameters using AI and accidentally undid some safety mechanism
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: