Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
luke-stanley
6 months ago
|
parent
|
context
|
favorite
| on:
Refusal in language models is mediated by a single...
Related comments:
https://news.ycombinator.com/item?id=40242939
I pointed out that you can use llama.cpp to do something like this with it's Classifier-Free Guidance (CFG) feature (may be easier than using Pytorch or such).
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: