Hacker News Reader

Comment by amelius | Hacker News Reader

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.

View on HN

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

I don't see the term used in the article.

its not a Claude-specific term

Prompts are not specs.

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.

This reminds me of the halfbakery website from older times.

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]."

Do we have reproducible LLMs?

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

Proponents of LLM coding agents would claim you don’t need reproducibility. As long as the final output passes tests/lint, it’s (allegedly) good to go.

If every build is different, no two builds will have the same bug/exploit, so maybe better security??

Reply on news.ycombinator.com