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 inference is bringing fresh attention to optical computing, which uses light rather than electricity for operations such as matrix-vector multiplication. IEEE Spectrum describes a field with promising energy-efficiency potential, but some decidedly unglamorous engineering hurdles remain.

Why it matters

The article says optical systems could improve efficiency as vector lengths grow. It also points to the hard parts: encoding data, scaling systems and integrating them with conventional electronics. That makes optical computing a promising direction, not a ready-made answer to AI’s power demands. Which should matter more in judging it: potential efficiency gains, or proof that the systems can scale and fit into today’s hardware?

Discuss: Which should matter more in judging optical computing: potential efficiency gains, or proof that the systems can scale and fit into today’s hardware?

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.