Re:Claude Cowork Exfiltrates Files
by ramoz on Wednesday January 14, 2026 @04:15PM
(#46623560)
One concern nobody likes to talk about is that this might not be a problem that is solvable even with more sophisticated intelligence - at least not through a self-contained capability. Arguably, the risk grows as the AI gets better.
[ Parent
| on HN ]
Re:Claude Cowork Exfiltrates Files
by hakanderyal on Wednesday January 14, 2026 @04:19PM
(#46623627)
Solving this probably requires a new breakthrough or maybe even a new architecture. All the billions of dollars haven't solved it yet. Lethal trifecta [0] should be a required reading for AI usage in info critical spaces.
[0]: https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/
Right. It might be even as complicated as requiring theoretical solutions or advancements of Rice's and Turing's.
Re:Claude Cowork Exfiltrates Files
by NitpickLawyer on Wednesday January 14, 2026 @04:27PM
(#46623777)
> this might not be a problem that is solvable even with more sophisticated intelligence
At some level you're probably right. I see prompt injection more like phishing than "injection". And in that vein, people fall for phishing every day. Even highly trained people. And, rarely, even highly capable and credentialed security experts.
"llm phishing" is a much better way to think about this than prompt injection. I'm going to start using that and your reasoning when trying to communicate this to staff in my company's security practice.
That's one thing for sure.
I think the bigger problem for me is the rice's theorem/halting problem as it pertains to containment and aspects of instrumental convergence.
Re:Claude Cowork Exfiltrates Files
by choldstare on Wednesday January 14, 2026 @04:40PM
(#46623971)
this is it.
Re:Claude Cowork Exfiltrates Files
by venturecruelty on Wednesday January 14, 2026 @08:51PM
(#46626917)
Oh, I love talking about it. It makes the AI people upset tho.