Re:GPT‑6 and Intelligent UI for everyone
by MaliaMarus on Thursday October 08, 2026 @06:07AM
(#50003931)
They aren't. They are saying that putting this safeguard at the level of the agent execution is a waste of time, particularly that of the researchers' expensive manhourse, especially now that existing smaller models can just evaluate the output.
[ Parent
| on HN ]
There are no comments on this comment yet.