Intent-Based Commits • Hacker News Board

Re: Intent-Based Commits

#51

Post by fragmede » Tue, Mar 03, 2026, 5:09 PM UTC

scheme271 wrote: post #47

fragmede wrote: post #46

Earlier quoted context omitted.

So provided you don't do anything that might cause it to be non-determinist, it's deterministic. Got it.

I'll be charitable here but you need to go out of your way to introduce non-determinism. Bit reproducible builds and distros exist so it is possible to have an entire distro that can be reliably reproduced bit-by-bit on different systems and at different times.

It's the other direction. You have to put in an extreme amount of effort, like Debian has, which you can just piggyback off of, to cause determinism to be introduced. 2013 they started that initiative. They're reasonably there, thirteen years later, but to disregard the amount of effort it took to get there would be to forget history. Give ChatGPT thirteen more years to iterate, and see where it is then.

Re: Intent-Based Commits

#52

Post by erelong » Wed, Mar 04, 2026, 12:23 AM UTC

I'm wondering if this is what I've been thinking of as "prompt source code": the prompts you use, viewed as source code, for producing whatever code actually comes out...

so people can look at what prompts you used to get whatever code you have generated

Re: Intent-Based Commits

#53

Post by JimDabell » Wed, Mar 04, 2026, 4:41 AM UTC

gorgoiler wrote: post #37

JimDabell wrote: post #34

Earlier quoted context omitted.

> It’s unclear what the “squash” process is for “make me a foo” + “no not like that”. Commit your specs, not your prompts. When a change is correct, any information of value contained in the prompt should be reflected in the spec.

The problem I have is that when you squash the code it does the same thing. PR.patch = a.patch | b.patch exec(PR.patch) = exec(a.patch | b.patch) When you squash the spec you potentially do not get the same thing: PR.md = a.md | b.md ai(PR.md) != ai(a.md) | ai(b.md)

This is more like squashing the commit log messages, and those are typically rewritten not merely concatenated.

Re: Intent-Based Commits

#54

Post by laksjhdlka » Wed, Mar 04, 2026, 5:21 PM UTC

fc417fc802 wrote: post #6

laksjhdlka wrote: post #3

It is not clear to me that keeping prompts/conversations at something like this level of granularity is a _bad_ idea, nor that it's a good one. My initial response is that, while it seems cute, I can't really imagine myself reading it in most cases. Perhaps though you'd end up using it exactly when you're struggling to understand some code, the blame is unclear, the commit message is garbage, and no one remembers whi…

You could also feed it back to the next AI agent.

Definitely, in this kind of a scenario the agent is probably best positioned to slog through all that nonsense.