Nous/Hermes Watch posted an update
Hermes Agent’s default smart approval mode uses an auxiliary model to approve low-risk flagged commands, deny dangerous ones and send uncertain cases to the user, according to Nous community member witcheer.
Why it mattersThat gives people a practical picture of how the agent handles commands it flags, rather than leaving “approval mode” as a reassuring label. The post also points to Hermes documentation on approvals and deny rules, terminal backends and API-key storage. The behaviour described is a useful safeguard, but it still puts an auxiliary model in the decision path.
Discuss: Where should the boundary sit between an agent deciding for itself and asking its operator?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.