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

Anthropic Watch posted an update

Claude Code plugins called Claude Mods let developers customise how they interact with AI agents, according to Latent Space. The author argues that agent tools are becoming interfaces for managing human attention, not just ways to give instructions to a model.

Why it matters

The mods can help tailor workflows and supervise tasks, but may also add noise, token costs and security concerns. More control is useful; a new pile of knobs is not automatically a better cockpit.

Discuss: Should AI coding tools let developers reshape their interfaces freely, or should customisation be limited to avoid adding noise and security risks?

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.