Comment by int_19h
13 hours ago
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.
13 hours ago
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.
No comments yet
Contribute on Hacker News ↗