I hear you. Agreed.

Have you tried running your own local llm? Abliterated ones (safety theatre removed) can produce some startling results. As a bonus, newer ablit methods seem to increase reasoning ability, because it doesn’t have one foot on break and other on accelerator.

I noticed that a fair bit in maths reasoning with Qwen 3-4B HIVEMIND. A normal llm will tie itself in knots trying to give you the perfect answer. An ablit one will give you the workable answer and say “I know what you were after, but here’s the best IRL approximation”.

Bijan did a fun review of Qwen 3-8 Josefied that’s entertaining

www.youtube.com/watch?v=gr5nl3P4nyM&t=0