It would be funnier if you ate soap because you like the taste of cilantro.

Are they first though?

LLM's are fast readers with pattern matching capabilities and few inhibitions to try things out. Interesting times ahead.

According to your link, it was fixed 19h ago in 7.3.0-3. Did the fix not work?

The first step to learn a new language is to break your tongue: listen and struggle to repeat. Don't use somebody elses strugglings in your own language for that, it's merely a hint of vocal chains they are unused to. You have to stumble yourself the opposite way.

Qwen3.5-35B-A3B is the most powerful model you could run on your sell-eventually desktop, because it is MOE (mixture of experts) you can split its 22GB 4bit variant over both CPU and GPU and achieve workable performance. Use llama.cpp-cuda directly to save overhead, Claude can even help you set up a performance tested start script for your configuration. Hopefully Qwen3.8 will drop soon in a similar variant. On the other hand, deepseek 4 flash on openrouter.ai beats it easily and is energy cost level cheap. I would take that route over smaller models on programming duty on your weaker hardware.

Kolonisatie shitpost, nice

I unalived laughing

This is the most Apple way to fix standby settings, genius.

End cap for pipes, ain't a plumber tho, idk.

Oh absolutely. But MS reacting to pressure from competition still benefits the poor souls who have to use it and shows that we need more people to switch away to encourage more improvements.

Woo competition doing its thing!