Viewing profile — djx22

Actually, this paper shows that the LLMs create a lot more slop and degradation of the code after the first prompt. https://arxiv.org/html/2603.24755v1 . So iterating with the LLM …

yes, I understand the usecase. Where I'm coming from is quantized vs. unquantized. 4bit quants are lobotomizing the model heavily to the point that it's better to invest in some ca…

similar experience, yes. I cancelled my subscription.

Not sure what everyone's experience is but I find 5.6 Sol to be a great liar. Reported success on a half done job and left things in a broken state after having quite a few back & …

in my experience running models that have been heavily quantized(q4) or altered to some extent has never made me say “wow, this is so amazing”. On the contrary, the model ended up …

Don't let AI write code for you unless it's something trivial. Instead use it to plan things, high level stuff, discuss architecture, ask it to explain concepts. Use it as a resear…