knowing which model to use is more important than the prompt

Decentralized open source consciousness | Values-aligned communities | citizen of Black Rock City

o3 is best when giving codebase context and acting as an architect/planner

claude 4 opus is absolutely ripping defined PRDs

gemini 2.5 is best for specific small tasks

gpt 4.5 is my favorite writer, gemini a close second

o3/4o is the best image generator

Idk can’t tell the difference between the SOTA ones

regrettably this is also the most arcane art

I switched to deepseek on one of my experiments and it messed up the whole project lmao

Just plug the prompt into multiple models 🤷‍♂️

this reply funds your work - drip drip drip @noiceapp

nah, prompt is super important + context, Json prompts rule