Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Intent-Based Commits

github.com

Post reply on HN
Print view View original

41–50 of 54 posts

Re: Intent-Based Commits

#41

Post by ares623 »

fragmede wrote: post #27
scheme271 wrote: post #19

> Every commit is reproducible. The prompt is preserved with > some extra attributes about which model and agent was used. > You can re-run any commit against a fresh checkout to see > what Claude generates from the same instruction. I don't see how this is true. LLMs can generate different outputs even with the same model and inputs.

How different? So do compilers.

Folks who bring up these "gotchas" should be forbidden from using or taking advantage of the things they are disingenuously whataboutism-ing. Reminds me of sovereign citizen behavior.

Re: Intent-Based Commits

#42

Post by geon »

We already have a very succinct and precise way to communicate intent. It's called source code.

Write your code so that the intent is crystal clear. If it is not, you have failed.

The primary purpose of code is NOT for a computer to execute it, but for humans to communicate intent.

Re: Intent-Based Commits

#43

Post by apsurd »

vtemian wrote: post #33

[flagged]

I don't think people read prompt sessions, not even their own. Instinctively I think the sessions are valuable because they capture how we arrived at the thing. in practice it's just "slop" to everyone that wasn't there when it was happening. including future you.

i'm mostly just musing. I get the instinct, but i suspect all sessions have extremely rapid decay cycles.

Re: Intent-Based Commits

#44

Post by apsurd »

sheept wrote: post #4

In my CLAUDE.md, I have Claude include all new prompts verbatim in the commit message body. While I haven't used Claude long enough to need my prompts, I would appreciate seeing my coworkers' prompts when I review their LLM-generated code or proposals. Sometimes it's hard to tell if something was intentional that the author can stand behind, or fluff hallucinated by the LLM. It's a bit annoying to ask why something s…

That sounds like a ton of cognitive effort.

Re: Intent-Based Commits

#46

Post by fragmede »

scheme271 wrote: post #39
fragmede wrote: post #27

Earlier quoted context omitted.

How different? So do compilers.

If you have a compiler the same source code and the same options, it should generate the same output everything provided you aren't using some compiler pragmas or something similar that embeds timestamps or random numbers or similar. If you give an LLM the same input, it can generate different outputs (controlled by the temperature setting).

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

Re: Intent-Based Commits

#47

Post by scheme271 »

fragmede wrote: post #46
scheme271 wrote: post #39

Earlier quoted context omitted.

If you have a compiler the same source code and the same options, it should generate the same output everything provided you aren't using some compiler pragmas or something similar that embeds timestamps or random numbers or similar. If you give an LLM the same input, it can generate different outputs (controlled by the temperature setting).

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.

Re: Intent-Based Commits

#48

Post by arcadianalpaca »

gorgoiler wrote: post #15

It would be good to see a real example. There’s a sketch of one in the README.md but I’d be interested to see how it works in real life with something complicated. > Add users with authentication > No, not like that > Closer, but I don’t want avatars > I need email validation too > Use something off the shelf? Someone in this place was saying this the other day: a lot of what might seem like public commits to main ar…

Yeah the squash question is the whole thing. If your commit history is "do X" -> "no, not like that" -> "closer" then your final commit message is just "do X" with no trace of why certain approaches were rejected. Which is arguably the most useful part of the conversation.

Re: Intent-Based Commits

#50

Post by miceeatnicerice »

geon wrote: post #42

We already have a very succinct and precise way to communicate intent. It's called source code. Write your code so that the intent is crystal clear. If it is not, you have failed. The primary purpose of code is NOT for a computer to execute it, but for humans to communicate intent.

It's surely supposed to be the perfect bridge between both - but we know in practice it often isn't.

I'd also quibble minorly with intent being what the code should be clearly communicating - it's its place and function and meaning within the wider system, which isn't necessarily what the particular programmer wished. Free-form English is a good medium for intent - not so much for "what this thing actually does"

Post reply on HN