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

321–330 of 410 posts

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

#321

Post by xlii »

827a wrote: post #94

IMO: This might be a contrarian opinion, but I don't think so. Its much the same problem as asking, for example, if every single line you write, or every function, becomes a commit. The answer to this granularity is, much like anything, you have to think of the audience: Who is served by persisting these sessions? I would suspect that there is little reason why future engineers, or future LLMs, would need access to t…

> Its much the same problem as asking, for example, if every single line you write, or every function, becomes a commit.

As a huge fan of atomic commits I'd say that smallest logical piece should be a commit. I never seen "intention-in-a-commit", i.e. multiple changes with overarching goal influence reviews. There's usually some kind of ticket that can be linked to the code itself if needed.

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

#322

Post by anbende »

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…

Here’s how I do the same thing, just with a slightly different wrapper: I’m running my own stepwise runtime where agents are plugged into defined slots.

I’ll usually work out the big decisions in a chat pane (sometimes a couple panes) until I’ve got a solid foundation: general guidelines, contracts, schemas, and a deterministic spec that’s clear enough to execute without interpretation.

From there, the runtime runs a job. My current code-gen flow looks like this: 1. Sync the current build map + policies into CLAUDE|COPILOT.md 2. Create a fresh feature branch 3. Run an agent in “dangerous mode,” but restricted to that branch (and explicitly no git commands) 4. Run the same agent again—or a different one—another 1–2 times to catch drift, mistakes, or missed edge cases 5. Finish with a run report (a simple model pass over the spec + the patch) and keep all intermediate outputs inspectable

And at the end, I include a final step that says: “Inspect the whole run and suggest improvements to COPILOT.md or the spec runner package.” That recommendation shows up in the report, so the system gets a little better each iteration instead of just producing code.

I keep tweaking the spec format, agent.md instructions and job steps so my velocity improves over time.

--- To answer the original article's question. I keep all the run records including the llm reasoning and output in the run record in a separate store, but it could be in repo also. I just have too many repos and want it all in one place.

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

#323

Post by wek »

jumploops wrote: post #205
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…

I do something similar, but across three doc types: design, plan, and debug Design works similar to your project.md file, but on a per feature request. I also explicitly ask it to outline open questions/unknowns. Once the design doc (i.e. design/[feature].md) has been sufficiently iterated on, we move to the plan doc(s). The plan docs are structured like `plan/[feature]/phase-N-[description].md` From here, the agent…

Similar, but we have the agent write the test cases after writing the plan and then iterate until it passes the test cases.

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

#326

Post by adampunk »

D-Machine wrote: post #79

Obviously yes, at least if not the prompts in the session, some simple / automated distillation of those prompts. Code generated by AI is already clearly not going to be reviewed as carefully as code produced by humans, and intentions / assumptions will only be documented in AI-generated comments to some limited degree, completely contingent on the prompt(s). Otherwise, when fixing a bug, you just risk starting from…

Just out of curiosity, what session size do you think we're talking about here?

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

#327

Post by ryanmcl »

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…

[dead]

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

#328

Post by adampunk »

mannanj wrote: post #42
causal wrote: post #37

If a car is used to get you somewhere, should you put the exhaust in bags to bring with you?

Is session context car exhaust? Or is it the Event logs and code of the CPU/car's brains?

It's exhaust. Retrospectively, chat is essentially worthless. You're going to chase hallucinations down conversations that maybe didn't even impact code.

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

#329

Post by thearn4 »

adam_patarino wrote: post #316
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…

You check the plan files into git? Don’t you end up with dozens of md files? I’ve been copying and pasting the plan into the linear issue or PR to save it, but keep my codebase clean.

Yeah I had the same question. I suppose you could put the project+plan text into the commit message?

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

#330

Post by mannanj »

adampunk wrote: post #328
mannanj wrote: post #42

Earlier quoted context omitted.

Is session context car exhaust? Or is it the Event logs and code of the CPU/car's brains?

It's exhaust. Retrospectively, chat is essentially worthless. You're going to chase hallucinations down conversations that maybe didn't even impact code.

I have difficulty believing chat is worthless.

And I think that not everyone will entertain or chase the hallucinations down. Or maybe enough non-hallucinations are chased that it is valuable.

Post reply on HN