What you're describing as pre-programming is a little misleading if the "pre-programming" doesn't need to change for each specific request: a real product would provide that "pre-programming" for the user.
Prompting for task performance is fine as long as you're not expecting the end user to have to replicate your prompting. Your goal is to change model activations for a given input, the end user is similarly affected regardless of if you used a prompt or fine-tuned.
-
This task doesn't require fine-tuning though, zero-shot performance is enough:
I generated a mock schema from Home Assistant's API (https://data.home-assistant.io/docs/states/) and explicitly gave the model the option to ask for clarification, but it has no problem translating non-obvious commands into actions without asking for details:
Note those objects mirror Home Automation, you could hook that up today without any song and dance. Combine that with RAG and you'd have something that's a lot more useful than Siri and capable of improving performance over time.
Prompting for task performance is fine as long as you're not expecting the end user to have to replicate your prompting. Your goal is to change model activations for a given input, the end user is similarly affected regardless of if you used a prompt or fine-tuned.
-
This task doesn't require fine-tuning though, zero-shot performance is enough:
I generated a mock schema from Home Assistant's API (https://data.home-assistant.io/docs/states/) and explicitly gave the model the option to ask for clarification, but it has no problem translating non-obvious commands into actions without asking for details:
https://chat.openai.com/share/fc5b972f-4641-47a1-9842-2e0d69...
Note those objects mirror Home Automation, you could hook that up today without any song and dance. Combine that with RAG and you'd have something that's a lot more useful than Siri and capable of improving performance over time.