Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
int_19h
54 days ago
|
parent
|
context
|
favorite
| on:
Heretic: Automatic censorship removal for language...
It goes both ways. E.g. unmodified thinking Qwen is actually easier to jailbreak to talk about things like Tiananmen by convincing it that it is unethical to refuse to do so.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: