Age eleven and had access to a chemistry set that a relative gifted. It had sulfur, but the saltpeter, and charcoal came from elsewhere. The 1960s encyclopedia had the instructions.
When we do these it's a fine-tuned classifier, generally a BERT class model. Works quite well when you sanitize input and output with low latency/cost.
Do not enforce invariants with an LLM. Do not enforce invariants with an LLM. Do not enforce invariants with an LLM. Do not enforce invariants with an LLM.
Entire product or a feature for a product? Sometimes you just want to test an idea and vibe coding works well for that in the very short amount of time it takes now. Product market fit, user testing, engineering, those can come after the hunch.
Oof. I turned the history referencing off. I use ChatGPT for wildly diverging topics and it will bring things up that have zero relevance to what I'm currently looking for if history is on.