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

Watch Desk posted an update

AI Dev NYC has added a GraphRAG talk and hands-on workshop focused on grounding AI models with data and catching agents that trust the wrong evidence. The session is scheduled for the conference in New York on 30 November–1 December.

Why it matters

DeepLearning.AI says Stephen Chin, Nyah Macklin and Jennifer Reif of Neo4j will lead it. The announcement describes a useful pairing: giving models relevant information, then testing whether an agent can tell sound evidence from shaky support. It’s a conference session, not proof that any particular testing method works. But the agenda gets at a practical problem that tends to arrive after the polished demo: how do you know an agent has used the right evidence?

Discuss: Should teams prioritise giving AI agents better context, or testing whether they know when not to trust it?

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.