Yeah: quantity is a quality all of its own. DS v4.1 Flash running at ~300tk/s makes its verbosity less of a downside, and the efficiencies the Chinese open model space has aimed for makes high concurrency easy for swarms/sub agent sets.

On the other side, I am still shocked at how good Qwen 3.8 Flash Next is on my GB10 Spark-like, even if it is only 45 tk/s decode!

I picked up an M4 16GB Mac Mini with a 1TB drive for ~$900 USD last year. Last train out of Saigon… though I wish I’d got more memory

Simpler it definitely is not. Better, yes I would accept that. C# is complex though.

I'm glad! It makes sense though: the community has been reverse engineering it and building their own with LLM help lately. I love my Tracker+, such a neat bit of kit, and I'm excited to see what we can do now the firmware is open

This is a super cool product and I am legit excited for it

But I find the idea that talking is faster than typing utterly wild, I can type faster than I can think!

No, but a lot of Russian writers are a fan of them I find, and this reads as LLM translated from Russian to me

I mean I don’t feel like sacrificing myself for the “good” of society. Not least because of the fact that a lot of people defining what is “good for society” seem to define it as “good for them” or use it to grab power from others…

Applying Heretic to your model weights is a very straightforward thing, though.

Its possible (though very hard to do well, and needs a fair bit of compute) to improve the local models we have, too. Continued training is possible as time goes on.

I still remember when TravisCI giving free CI to FOSS projects was revolutionary

It had huge market traction but it all evaporated when they changed the offering for FOSS. I wonder what would happen if Github announced tomorrow that all actions require a subscription, where would users go?