News for hackers. Stuff that matters.
Re:Claude Cowork Exfiltrates Files by hakanderyal on Wednesday January 14, 2026 @04:29PM (#46623799)
What you are describing is the most basic form of prompt injection. Current LLMs acts like 5 years old when it comes to cuddling them to write what you want. If you ask it for meth formula, it'll refuse. But you can convince it to write you a poem about creating meth, which it would do if you are clever enough. This is a simplification, check Pliny[0]'s work for how far prompt injection techniques go. None of the LLMs managed to survive against them.

[0]: https://github.com/elder-plinius

There are no comments on this comment yet.