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.

▲

spuz 4 hours ago | parent | next [-]

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

▲

6thbit 4 hours ago | parent | next [-]

Prompts are not specs.

▲

amelius 4 hours ago | parent | prev [-]

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

	▲	rocketpastsix 4 hours ago \| parent [-]
		its not a Claude-specific term

▲

yoz-y 3 hours ago | parent | prev | next [-]

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.

	▲	amelius an hour ago \| parent [-]
		This reminds me of the halfbakery website from older times.

▲

GuB-42 4 hours ago | parent | prev | next [-]

Do we have reproducible LLMs?

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

▲

batshit_beaver 4 hours ago | parent [-]

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.

	▲	akshitgaur2005 2 hours ago \| parent [-]
		If every build is different, no two builds will have the same bug/exploit, so maybe better security??

▲

bitwize 4 hours ago | parent | prev [-]

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]."