News for hackers. Stuff that matters.
Re:Show HN: BadSeek – How to backdoor large language models by twno1 on Friday February 21, 2025 @09:26AM (#43127798)
Reminds me this research done by Anthropic. https://www.anthropic.com/research/sleeper-agents-training-d...

And the method of probes for Sleeper Agents in LLM https://www.anthropic.com/research/probes-catch-sleeper-agen...

There are no comments on this comment yet.