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

If AI writes code, should the session be part of the commit?

github.com

Post reply on HN
Print view View original

291–300 of 410 posts

Re: If AI writes code, should the session be part of the commit?

#291

Post by xmcqdpt2 »

D-Machine wrote: post #125
tpmoney wrote: post #110

Earlier quoted context omitted.

You have the source code though. That is the "reproducibility" bit you need. What extra reproducibility does having the prompts give you? Especially given that AI agents are non-deterministic in the first place. To me the idea that the prompts and sessions should be part of the commit history is akin to saying that the keystroke logs and commands issued to the IDE should be part of the commit history. Is it important…

> You have the source code though. That is the "reproducibility" bit you need. I am talking about reproducing the (perhaps erroneous) logic or thinking or motivations in cases of bugs, not reproducing outputs perfectly. As you said, current LLM models are non-deterministic, so we can't have perfect reproducibility based on the prompts, but, when trying to fix a bug, having the basic prompts we can see if we run into…

It's not reproducible though.

Even with the exact same prompt and model, you can get dramatically different results especially after a few iterations of the agent loop. Generally you can't even rely on those though: most tools don't let you pick the model snapshot and don't let you change the system prompt. You would have to make sure you have the exact same user config too. Once the model runs code, you aren't going to get the same outputs in most cases (there will be date times, logging timestamps, different host names and user names etc.)

I generally avoid even reading the LLM's own text (and I wish it produced less of it really) because it will often explain away bugs convincingly and I don't want my review to be biased. (This isn't LLM specific though -- humans also do this and I try to review code without talking to the author whenever possible.)

Re: If AI writes code, should the session be part of the commit?

#292

Post by jwrallie »

veunes wrote: post #273

The idea of "saving prompts for reproducibility" is dead on arrival. LLMs are non-deterministic by nature. In a year, they'll deprecate this model's API, and the new version will spit out completely different code with entirely new bugs for the exact same prompt. A prompt isn't source code, it's just a temporary crutch for stochastic generation. And if I have to read 50 pages of schizophrenic dialogue with an LLM jus…

This is something that should be possible in principle, since the machines underneath are deterministic, it’s just a limitation of the implementation.

Re: If AI writes code, should the session be part of the commit?

#293

Post by addcn »

rfw300 wrote: post #14

Why should it be? The agent session is a messy intermediate output, not an artifact that should be part of the final product. If the "why" of a code change is important, have your agent write a commit message or a documentation file that is polished and intended for consumption.

This reduces down to the problem of summarization - a quite difficult one. At commit time it’s difficult to know what questions readers will have. You can get close but never all the way there.

Pre AI when engineers couldn’t find the answer in commit messages or documentation they would ask the author “why” and that human would “compute” the summary on demand.

I think that’s what I expect to do with these agent sessions - I don’t want more markdown, I want to ask it questions on demand. Git AI (https://github.com/git-ai-project/git-ai) uses the prompts that way. I think that model will win out. Save sessions. Read/ask questions relevant to the current agent’s work.

On asking peers. This is regrettably on the way out today - I’ll ask engineers about complex code they generated and they can’t give good answers. I think it’s because it all happened so fast — they didn’t sit with the problem for 48 hours. So even if they steered the agent thoughtfully it’s hard to remember all the decisions they made a week later.

Re: If AI writes code, should the session be part of the commit?

#294

Post by xmcqdpt2 »

ahupp wrote: post #83
monster_truck wrote: post #55

Earlier quoted context omitted.

this is what granular commits are for, the kilobytes long log of claude running in circles over bullshit isn't going to help anyone

I think the parent comment is saying “why did the agent produce this big, and why wants it caught”, which is a separate problem from what granular commits solve, of finding the bug in the first place.

There is no "why." It will give reasons but they are bullshit too. Even with the prompt you may not get it to produce the bug more than once.

If you sell a coding agent, it makes sense to capture all that stuff because you have (hopefully) test harnesses where you can statistically tease out what prompt changes caused bugs. Most projects wont have those and anyway you don't control the whole context if you are using one of the popular CLIs.

Re: If AI writes code, should the session be part of the commit?

#295

Post by dmd »

jedberg wrote: post #173

The way I write code with AI is that I start with a project.md file, where I describe what I want done. I then ask it to make a plan.md file from that project.md to describe the changes it will make (or what it will create if Greenfield). I then iterate on that plan.md with the AI until it's what I want. I then ask it to make a detailed todo list from the plan.md and attach it to the end of plan.md. Once I'm fully sa…

https://github.com/obra/superpowers "brainstorming" is pretty much exactly this workflow, and it's great.

Re: If AI writes code, should the session be part of the commit?

#296

Post by newswasboring »

D-Machine wrote: post #125
tpmoney wrote: post #110

Earlier quoted context omitted.

You have the source code though. That is the "reproducibility" bit you need. What extra reproducibility does having the prompts give you? Especially given that AI agents are non-deterministic in the first place. To me the idea that the prompts and sessions should be part of the commit history is akin to saying that the keystroke logs and commands issued to the IDE should be part of the commit history. Is it important…

> You have the source code though. That is the "reproducibility" bit you need. I am talking about reproducing the (perhaps erroneous) logic or thinking or motivations in cases of bugs, not reproducing outputs perfectly. As you said, current LLM models are non-deterministic, so we can't have perfect reproducibility based on the prompts, but, when trying to fix a bug, having the basic prompts we can see if we run into…

You are talking about documenting the intent of a piece of software if I understand correctly. But isn't that what READMEs and comments are for?

Re: If AI writes code, should the session be part of the commit?

#297

Post by neomantra »

raggi wrote: post #57

nope. Someones going to leak important private data using something like this. Consider: "I got a bug report from this user: ... bunch of user PII ..." The LLM will do the right thing with the code, the developer reviewed the code and didn't see any mention of the original user or bug report data. Now the notes thing they forgot about goes and makes this all public.

I agree with you, but also we will start sharing these conversation traces more and more. That's why it is important for redaction to be in the export pipeline. There can be both deterministic (eg regex) and LLM-based redaction.

Re: If AI writes code, should the session be part of the commit?

#298

Post by aspenmartin »

xmcqdpt2 wrote: post #294
ahupp wrote: post #83

Earlier quoted context omitted.

I think the parent comment is saying “why did the agent produce this big, and why wants it caught”, which is a separate problem from what granular commits solve, of finding the bug in the first place.

There is no "why." It will give reasons but they are bullshit too. Even with the prompt you may not get it to produce the bug more than once. If you sell a coding agent, it makes sense to capture all that stuff because you have (hopefully) test harnesses where you can statistically tease out what prompt changes caused bugs. Most projects wont have those and anyway you don't control the whole context if you are using…

If I have a session history or histories, I can (and have!) mine them to pinpoint where an agent either did not implement what it was supposed to, or understand who asked for a certain feature an why, etc. It complements commits, sessions are more like a court transcript of what was said / claimed (session) and then you can compare that to what was actually done (commits).

Re: If AI writes code, should the session be part of the commit?

#300

Post by FpUser »

I keep trunk of conversation internally. No way I am putting it on github. The way I think, plan, interrogate LLM is part of competitive advantage in the market. I consider it my property and I would not ever let my clients read it (I pay for my usage of AI). Never mind some juicy language and being super straight and apolitical in a corporate sense. basically would be a major privacy breach
Post reply on HN