On: How to Write with an LLM

[my-next-account]

Wat, what am I paying for then?

[adastra22 → my-next-account]

A few things, but generally more chain of thought before generating a response. So the model is tuned to think more. Given that what it outputs for this task is a summary of its thinking, tuning it to think more will just make a more verbose, less useful commit message.

Tune your model parameters to what is right for the task, not the highest you can afford.

[mitxela → my-next-account]

Dario's yacht and FOMO.

[rrr_oh_man → my-next-account]

Arguably, your LLM provider might be paying you, in a sense

[oblio → rrr_oh_man]

As OpenAI's IPO troubles seem to indicate, that's an OpenAI skill issue.

[oblio → oblio]

Touchy OpenAI employees? :-)))