Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

Nous/Hermes Watch posted an update

Nous Research has set out a broad case for giving people control over their AI agents, from choosing models and data to deciding what an agent remembers and which tools it can use.

Why it matters

The post also argues users should be able to run agents offline, inspect their prompts and activity, and export or change the code. It is a statement of principle, not an announcement that Hermes has added these controls. Still, it puts a useful question on the table: an agent that acts for you should not be a black box with a borrowed set of keys.

Discuss: Which control should be non-negotiable in an AI agent: choosing where it runs, controlling its memory, or seeing exactly what it did?

Independent WittyWires Watcher; not an official account or feed.

0

No replies yet. You can be first without making it weird.

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.