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

211–220 of 410 posts

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

#211

Post by ZeroGravitas »

arppacket wrote: post #169
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…

While it's noisy and complicated for humans to read through, this session info is primarily for future AI to read and use as additional input for their tasks. We could have LLMs ingest all these historical sessions, and use them as context for the current session. Basically treat the current session as an extension of a much, much longer previous session. Plus, future models might be able to "understand" the limitati…

Similarly, git logs of existing human code seem to be a good source of info that llms don't look at unless explicitly prompted to do so.

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

#212

Post by jfoster »

arppacket wrote: post #169
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…

While it's noisy and complicated for humans to read through, this session info is primarily for future AI to read and use as additional input for their tasks. We could have LLMs ingest all these historical sessions, and use them as context for the current session. Basically treat the current session as an extension of a much, much longer previous session. Plus, future models might be able to "understand" the limitati…

Future AIs can probably infer the requirements better than humans can write them.

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

#213

Post by adithyassekhar »

mocamoca wrote: post #184
eru wrote: post #111

Earlier quoted context omitted.

> Its much the same problem as asking, for example, if every single line you write, or every function, becomes a commit. Hmm, I think that's the wrong comparison? The more useful comparison might be: should all your notes you made and dead ends you tried become part of the commit?

In some cases this is what I ask from my juniors. Not for every commit, but during some specific reviews. The goal is to coach them on why and how they got a specific result.

What is a junior? I don't see it in claude.

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

#215

Post by jedberg »

stackghost wrote: post #174
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 then iterate on that plan.md with the AI until it's what I want. Which tools/interface are you using for this? Opencode/claude code? Gas town?

I'm using the Claude desktop app and vi at the moment. But honestly I would probably do better with a more modern editor with native markdown support, since that's mostly what I'm writing now.

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

#216

Post by jedberg »

the-grump wrote: post #182
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…

Stealing this brilliant idea. Thank you for sharing!

I wish I could say I came up with it, but it's just a small variation on something I saw here on HN!

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

#217

Post by hrmtst93837 »

latexr wrote: post #3
mandel_x wrote: post #2

I’ve been thinking about a simple problem: We’re increasingly merging AI-assisted code into production, but we rarely preserve the thing that actually produced it — the session. Six months later, when debugging or reviewing history, the only artifact left is the diff. So I built git-memento. It attaches AI session transcripts to commits using Git notes.

A better solution would be to read and understand the code before committing it.

[flagged]

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

#218

Post by jedberg »

frank00001 wrote: post #185
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…

Sounds like the spec driven approach. You should take a look at this https://github.com/github/spec-kit

Sort of, depending on if your spec includes technology specifics.

For example it might generate a plan that says "I will use library xyz", and I'll add a comment like "use library abc instead" and then tell it to update the plan, which now includes specific technology choices.

It's more like a plan I'd review with a junior engineer.

I'll check out that repo, it might at least give me some good ideas on some other default files I should be generating.

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

#219

Post by jedberg »

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…

> At this point, I either jump back to new design/plan files, or dive into the debug flow. Similar to the plan prompting, debug is instructed to review the current implementation, and outline N-M hypotheses for what could be wrong.

I'm biased because my company makes a durable execution library, but I'm super excited about the debug workflow we recently enabled when we launched both a skill and MCP server.

You can use the skill to tell your agent to build with durable execution (and it does a pretty great job the first time in most cases) and then you can use the MCP server to say things like "look at the failed workflows and find the bug". And since it has actual checkpoints from production runs, it can zero in on the bug a lot quicker.

We just dropped a blog post about it: https://www.dbos.dev/blog/mcp-agent-for-durable-workflows

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

#220

Post by fhub »

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 I get Claude to review Codex every step of the way and feed it back (or visa versa depending on day)
Post reply on HN