Choosing your model and your tool
- 01The model landscape, one family of predictors7 min
Claude, GPT, Gemini and open-weight models are all next-word predictors trained differently, and a prompt template written for one carries across to the others with barely any change.
- 02Route by task, not by brand7 min
Choosing a model is decided by the nature of the task, its stakes and its novelty, not by brand loyalty, and a more honest framing of a request often unlocks more than switching models does.
- 03Composing a system prompt across several providers7 min
When a prompt has to work across several providers, take each one's strongest rule, merge them without contradiction, and rules written by the prompt's owner generally outrank a provider's defaults, except when they would conflict with the safety limits that provider sets for itself.
- 04Local model, custom-built, or simply a better prompt6 min
An open-weight model run locally involves no cost charged per call and sends no data outside, a custom-built model costs a lot to construct and is only worth it at very high volume or for a fixed format, and in the vast majority of cases a better-written prompt solves the problem faster than either.