Comment by Forgeon1
1 day ago
do your own jailbreak tests with this open source tool https://x.com/ralph_maker/status/1915780677460467860
1 day ago
do your own jailbreak tests with this open source tool https://x.com/ralph_maker/status/1915780677460467860
A smaller piece of the puzzle, but I saw this refusal classifier by NousResearch yesterday and could be useful too https://x.com/NousResearch/status/1915470993029796303
https://github.com/rforgeon/agent-honeypot