On: A dark horse enters China's AI race: StartLux

[Karuma]

It's just another Qwen 3.6 27B finetune (not even 3.8...), claiming to beat TB-sized models. This is probably the 57th model like that, just this week, claiming the same thing... And they never deliver, to say the least.

[dgellow → Karuma]

Didn’t they deliver something here? Why does it matter what base model they used?

[eightysixfour → dgellow]

What they all deliver is benchmaxxed models that are awful in actual use.

[xena → eightysixfour]

But it gives the lab good publicity, as seen in the article.

[vkaku → eightysixfour]

I'm giving out more unpopular opinions today for entertainment and thought :)

Every model is benchmaxxing today. Many of them are awful until tuned for any particular task.

[dgellow → eightysixfour]

Qwen is a really awesome model to use!

[BoredomIsFun → Karuma]

> (not even 3.8...)

3.6 is better for non-coding tasks, noticeably so.

[alansaber → Karuma]

The finetunes will continue until morale increases.