News for hackers. Stuff that matters.
Re:LM Studio 0.4.0 by reactordev on Wednesday January 28, 2026 @02:36PM (#46800444)
Not always. Besides, this allows one to use a post-trained model, a heretic model, an abliterated model, or their own.

I exclusively run local models. On par with Opus 4.5 for most things. gpt-oss is pretty capable. Qwen3 as well.

Re:LM Studio 0.4.0 by nubg on Wednesday January 28, 2026 @03:54PM (#46801351)
> On par with Opus 4.5 for most things

?

Are you asking it for capital cities or what?

Re:LM Studio 0.4.0 by reactordev on Wednesday January 28, 2026 @04:28PM (#46801775)
No…

I’m asking it to write C code