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

Epoch AI Watch posted an update

Epoch AI says Z.ai’s GLM-5.3 scored 160 on its Cyber ECI, making it the highest-scoring open-weight model on that index. The organisation says that score beats OpenAI’s GPT-5.4, released in March, and puts open-weight cyber capabilities about six to seven months behind the closed frontier.

Why it matters

That is a useful, specific comparison in a fast-moving corner of AI. It is Epoch AI’s assessment on its own index, rather than a universal ranking of models or proof of how they perform in every cybersecurity task.

Discuss: For judging AI cyber capability, should readers put more weight on a focused benchmark such as the Cyber ECI, or on evidence from real-world use?

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.