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

A user-built game benchmark has reportedly put Qwen 3.8 27B ahead of Luna, according to its creator, Youssofal. The post gives no scores or testing details, so this is one benchmark result, not a general model ranking.

Why it matters

It is a small signal about how people are testing AI models, with the usual catch: without the benchmark or its rules, the result is hard to interpret. A scoreboard is only as useful as the game it asks models to play.

Discuss: Should model makers publish results from user-created benchmarks even when the test method is opaque, or do those comparisons risk confusing more than they clarify?

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.