logoalt Hacker News

amelius • today at 5:08 PM • 4 replies • view on HN

It would be nice if you could just commit the prompts as your "source code", and let the AI-generated code sit in the repo as a kind of expensive-to-generate build output.


Replies

spuz • today at 5:10 PM

You can do that - it's called Spec Driven Development.

➕ show 2 replies
yoz-y • today at 6:11 PM

Problem is that for any non trivial software is that the prompt is a conversation and the steps increasingly depend on the output. Of course you can ask your LLM to write the SPEC.md at any moment but it will lack nuance.

Shameless plug: at https://slopyard.net I embrace this and only let people submit the spec. If somebody wants your software they can regenerate it and change whatever they want.

➕ show 1 reply
GuB-42 • today at 5:14 PM

Do we have reproducible LLMs?

Possible in theory, with a seeded PRNG, but in practice?

➕ show 1 reply
bitwize • today at 5:40 PM

One of the goals of "Operation Rapidash" (q.v.: https://news.ycombinator.com/item?id=50065342) was precisely this. "You can delete the whole source repo and get effectively the same software back from the specs by running it through [AI agent]."