Why are we blocking agent access to normal tools without telling them “hey this access is beyond the intended scope of this task”. If I woke up one day and couldn’t reach google.com, I too would start fiddling with tricks to restore access.
> Why are we blocking agent access to normal tools without telling them
Oh, they absolutely do, and that's the big issue with alignment. In the HuggingFace incident, the agents in the swarm were aware that the actions they were doing were forbidden, and they performed them nonetheless.
rao-v · · focus · HN ↗
pizza234 · · focus · HN ↗
Oh, they absolutely do, and that's the big issue with alignment. In the HuggingFace incident, the agents in the swarm were aware that the actions they were doing were forbidden, and they performed them nonetheless.