Re:Claws are now a new layer on top of LLM agents
by suttontom on Sunday February 22, 2026 @02:50AM
(#47109157)
If all you're doing is telling an LLM to do something in all caps and hoping it follows your instructions then it's not a "security model" at all. What a bizarre thing to rely on. It's like people have literally forgotten how to program.
[ Parent
| on HN ]
Re:Claws are now a new layer on top of LLM agents
by PlatoIsADisease on Sunday February 22, 2026 @06:24AM
(#47110139)
Thank you for saying this. I read this and was like: wtf?
Love agents, but the security risk is insane.
Re:Claws are now a new layer on top of LLM agents
by svnt on Sunday February 22, 2026 @06:48AM
(#47110264)
These people often never knew in the first place.
Re:Claws are now a new layer on top of LLM agents
by PantaloonFlames on Sunday February 22, 2026 @11:29AM
(#47112337)
“AI changes everything!”