News for hackers. Stuff that matters.

A comment on Claws are now a new layer on top of LLM agents. Parent comment

Re:Claws are now a new layer on top of LLM agents by aix1 on Sunday February 22, 2026 @12:58AM (#47108624)
Is there a risk that the summary doesn't fully match the action that actually gets executed?
[ Parent | on HN ]
Re:Claws are now a new layer on top of LLM agents by faeyanpiraat on Sunday February 22, 2026 @04:00AM (#47109508)
Side note: Just like with a human employee asking for permission to do something.
[ Parent | on HN ]
Re:Claws are now a new layer on top of LLM agents by danparsonson on Sunday February 22, 2026 @06:31AM (#47110174)
Except for the accountability if they screw up; and the human brain thinking through what they are doing.
[ Parent | on HN ]
Re:Claws are now a new layer on top of LLM agents by ZitchDog on Friday February 27, 2026 @06:17PM (#47187343)
Nope! The summary is presented to the user via a link and once the user follows the link and approves, the action is implemented entirely outside of the agent, on a separate server.
[ Parent | on HN ]