Re:ChatGPT agent: bridging research and action
by itsalotoffun on Friday July 18, 2025 @06:13AM
(#44603024)
Exactly. You can't both give the model access AND enforce security. You CAN convince yourself you've done it though. You see it all the time, including in this thread.
[ Parent
| on HN ]
There are no comments on this comment yet.