zlacker

Yet another example of "comments that are only sort of true because high temperature sampling isn't allowed".

If you use LLMs at very high temperature with samplers which correctly keep your writing coherent (i.e. Min_p, or better like top-h, P-less decoding, etc), than "regression to the mean" literally DOES NOT HAPPEN!!!!

>>Der_Ei+(OP)
How do you configure LLM température in coding agents, e.g. opencode?

>>adevil+P
You can't without hacking it! That's my point! The only places you can easily are via the API directly, or "coomer" frontends like SillyTavern, Oobabooga, etc.

Same problem with image generation (lack of support for different SDE solvers, the image version of LLM sampling) but they have different "coomer" tools, i.e. ComfyUI or Automatic1111

>>Der_Ei+d1
Once again, porn is where the innovation is…

>>adevil+P
https://opencode.ai/docs/agents/#temperature

set it in your opencode.json

>>Der_Ei+(OP)
Have you actually tried high temperature values for coding? Because I don’t think it’s going to do what you claim it will.

LLMs don’t “reason” the same way humans do. They follow text predictions based on statistical relevance. So raising the temperature will more likely increase the likelihood of unexecutable pseudocode than it would create a valid but more esoteric implementation of a problem.

>>yoyohe+i2
Please.. "Creative Writing"

>>hnlmor+Kd
To put it another way, a high-temperature mad-libs machine will write a very unusual story, but that isn't necessarily the same as a clever story.

>>hnlmor+Kd
High temperature seems fine for my coding uses on GPT5.2.

Code that fails to execute or compile is the default expectation for me. That's why we feed compile and runtime errors back into the model after it proposes something each time.

I'd much rather the code sometimes not work than to get stuck in infinite tool calling loops.

>>Terr_+6m
So why is this "temperature" not on, like, a rotary encoder?

So you can just, like, tweak it when it's working against your intent in either direction?

>>kabr+93
Note when I said "you have to hack it in", I mean you'll need to hack in support for modern LLM samplers like min_p, which enables setting temperature up to infinity (given min_p approaching 1) while maintaining coherence.

>>balama+Pu
AFAIK there's no algorithmic reason against it, but services might not expose the controls in a convenient way, or at all.