60 comments

  • dang 23 minutes ago

    I floated that idea a week ago: https://news.ycombinator.com/item?id=47096202, although I used the word "prompts" which users pointed out was obsolete for this. "Session" seems better for now.

    The objections I heard, which seemed solid, are (1) there's no single input to the AI (i.e. no single session or prompt) from which such a project is generated,

    (2) the back-and-forth between human and AI isn't exactly like working with a compiler (the loop of source code -> object code) - it's also like a conversation between two engineers [1]. In the former case, you can make the source code into an artifact and treat that as "the project", but you can't really do that in the latter case, and

    (3) even if you could, the resulting artifact would be so noisy and complicated that saving it as part of the project wouldn't really add that much value.

    At the same time, people have been submitting so many Show HNs of generated projects, including nothing more than a generated repo with a generated readme. We need a better way of processing these because treating them like old-fashioned Show HNs is just overwhelming the system with noise right now [2].

    I don't want to exclude these projects, because (1) some of them are good, (2) there's nothing wrong with more people being able to create and share things, (3) it's foolish to fight the future, and (4) there's no obvious way to exclude them anyhow.

    But the status quo isn't great either because these projects, as things currently stand, are mostly not that interesting. What's needed is some additional support to make them more interesting.

    So, community: what should we do?

    [1] this point came from seldrige at https://news.ycombinator.com/item?id=47096903 and https://news.ycombinator.com/item?id=47108653.

    YoumuChan makes a similar point at https://news.ycombinator.com/item?id=47213296, comparing it to Google search history. The analogy is different but the issue (signal/noise ratio) is the same.

    [2] Is Show HN dead? No, but it's drowning - https://news.ycombinator.com/item?id=47045804 - Feb 2026 (422 comments)

    • sillysaurusx a minute ago

      Unfortunately Codex doesn’t seem to be able to export the entire session as markdown, otherwise I’d suggest encouraging people to include that in their Show HNs. It’s kind of nuts that it’s so difficult to export what’s now a part of the engineering process.

      I don’t have anything against vibe coded apps, but what makes them interesting is to see the vibe coding session and all the false starts along the way. You learn with them as they explore the problem space.

    • acedTrex 4 minutes ago

      > (2) there's nothing wrong with more people being able to create and share things

      There is very clearly many things wrong with this when the things being shown require very little skill or effort.

    • bandrami 8 minutes ago

      Plenty of commits link to mailing list discussions about the proposed change, maybe something like that, with an archive of LLM sessions?

  • rfw300 2 hours ago

    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.

    • sunir a minute ago

      In my case I have set up the agent is the repo. The repo texts compose the agents memory. Changes to the repo require the agent to approve.

      So I keep the agents semantically compressed as part of the repo as well as the original transcripts because often they lose coherence and reviewing every user submitted prompt realigns the specs and stories and requirements.

    • aspenmartin an hour ago

      post mortems / bug hunting -- pinpointing what part of the logic was to blame for a certain problem.

      • monster_truck 7 minutes ago

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

    • lacunary an hour ago

      but that takes more tokens and time. if you just save the raw log, you can always do that later if you want to consume it. plus, having the full log allows asking many different questions later.

    • AndrewKemendo an hour ago

      How’s it any different than a diff log?

      • xboxnolifes an hour ago

        Better question: how is it in any way similar?

        • AndrewKemendo 32 minutes ago

          If you read the history of both and assuming that there’s good comments and documentation, it shows you the reasoning that went into the decision-making

  • abustamam 43 minutes ago

    I don't think it should be. I think a distilled summary of what the agent did should be committed. This requires some dev discipline. But for example:

    Make a button that does X when clicked.

    Agent makes the button.

    I tell it to make the button red.

    Agent makes it red.

    I test it, it is missing an edge case. I tell it to fix it.

    It fixes it.

    I don't like where the button is. I tell it to put it in the sidebar.

    It does that.

    I can go on and on. But we don't need to know all those intermediaries. We just need to know Red button that does X by Y mechanism is in the sidebar. Tests that include edge cases here. All tests passing. 2026-03-01

    And that document is persisted.

    If later, the button gets deleted or moved again or something, we can instruct the agent to say why. Button deleted because not used and was noisy. 2026-03-02

    This can be made trivial via skills, but I find it a good way to understand a bit more deeply than commit messages would allow me to do.

    Of course, we can also just write (or instruct agents to write) better PRs but AFAICT there's no easy way to know that the button came about or was deleted by which PR unless you spelunk in git blame.

  • genghisjahn 11 minutes ago

    If you can, run several agents. They document their process. Trade offs considered, reasoning. Etc. it’s not a full log of the session but a reasonable history of how the code came to be. Commit it with the code. Namespace it however you want.

  • causal an hour ago

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

    • mannanj an hour ago

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

    • cyberax an hour ago

      We use flight data recorders on airplanes, though.

  • YoumuChan an hour ago

    Should my google search history be part of the commit? To that question my answer is no.

    • travisjungroth an hour ago

      I was looking for an analogy and this is a good one.

      The noise to signal ratio seems so bad. You’d have to sift through every little “thought”. If I could record my thought stream would I add it to the commit? Hell no.

      Now, a summary of the reasoning, assumptions made and what alternatives were considered? Sure, that makes for a great message.

      • rerdavies 10 minutes ago

        Heck no. I don't even read the vast majority of the cack that my AI spits out for my own prompts. Why would I inflict that on anyone else?

  • daemonk an hour ago

    I did this in the beginning and realized I never went back to it. I think we have to learn to embrace the chaos. We can try to place a couple of anchors in the search space by having Claude summarize the code base every once in a while, but I am not sure if even that is necessary. The code it writes is git versioned and is probably enough to go on.

  • daxfohl an hour ago

    I think so. If nothing else, when you deploy and see a bug, you can have a script that revives the LLMs of the last N commits and ask "would your change have caused this?" Probably wouldn't work or be any more efficient than a new debugging agent most of the time, but it might sometimes and you'd have a fix PR ready before you even answered the pager. And it's cheap, so why not.

    Maybe not a permanent part of the commit, but something stored on the side for a few weeks at a time. Or even permanently, it could be useful to go back and ask, "why did you do it that way?", and realize that the reason is no longer relevant and you can simplify the design without worrying you're breaking something.

  • mandel_x 4 hours ago

    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.

    • denismi an hour ago

      > the only artifact left is the diff

      You also have code comments, docs in the repo, the commit message, the description and comments on the PR, the description and comments on your Issue tracker.

      Providing context for a change is a solved problem, and there is relatively mature MCP for all common tooling.

    • latexr 3 hours ago

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

      • mandel_x 3 hours ago

        People won’t do that, unfortunately. We are a dying breed (I hate it). I went against my own instincts and vibe code this, works as a proof of concept.

        You can see the session (including my typos) and compare what was asked for and what you got.

    • midnitewarrior 2 hours ago

      I already invented this in my head, thanks for not making me code it.

      Excellent idea, I just wish GitHub would show notes. You also risk losing those notes if you rebase the commit they are attached to, so make sure you only attach the notes to a commit on main.

      • mandel_x an hour ago

        I added an action that will add a comment with the notes in GitHub so that you can see them directly.

        I did work around squash to collect all sessions and concatenate them as a single one

  • natex84 an hour ago

    If the model in use is managed by a 3rd party, can be updated at will, and also gives different output each time it is interacted with, what is the main benefit?

    If I chat with an agent and give an initial prompt, and it gets "aspect A" (some arbitrary aspect of the expected code) wrong, I'll iterate to get "aspect A" corrected. Other aspects of the output may have exactly matched my (potentially unstated) expectation.

    If I feed the initial prompt into the agent at some later date, should I expect exactly "aspect A" to be incorrect again? It seems more likely the result will be different, maybe with some other aspects being "unexpected". Maybe these new problems weren't even discussed in the initial archived chat log, since at that time they happened to be generated in a way in alignment with the original engineers expectation.

    • bear3r an hour ago

      reproducibility isn't really the goal imo. more like a decision audit trail -- same reason code comments have value even though you can't regenerate the code from them. six months later when you're debugging you want to know 'why did we choose this approach' not 'replay the exact conversation.'

    • fragmede an hour ago

      Because intent matters and 6 months or 3 years down the line and it's time to refactor, and the original human author is long gone, there's a difference if the prompt was "I need a login screen" vs "I need a login screen, it should support magic link login and nothing else".

      • superturkey650 an hour ago

        Isn’t that point of design docs and not the commit log?

  • ramoz 2 hours ago

    We think so as well with emphasis on "why" for commits (i.e. intent provenance of all decisions).

    https://github.com/eqtylab/y just a prototype, built at codex hackathon

    The barrier for entry is just including the complete sessions. It gets a little nuanced because of the sheer size and workflows around squash merging and what not, and deciding where you actually want to store the sessions. For instance, get notes is intuitive; however, there are complexities around it. Less elegant approach is just to take all sessions in separate branches.

    Beyond this, you could have agents summarize an intuitive data structure as to why certain commits exist and how the code arrived there. I think this would be a general utility for human and AI code reviewers alike. That is what we built. Cost /utility need to make sense. Research needs to determine if this is all actually better than proper comments in code

  • raggi 4 minutes ago

    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.

  • burntoutgray 2 hours ago

    YES! The session becomes the source code.

    Back in the dark ages, you'd "cc -s hello.c" to check the assembler source. With time we stopped doing that and hello.c became the originating artefact. On the same basis the session becomes the originating artefact.

    • lich_king an hour ago

      I'm not sure this analogy holds, for two reasons. First, even in the best case, chain-of-thought transcripts don't reliably tell you what the agent is doing and why it's doing it. Second, if you're dealing with a malicious actor, the transcript may have no relation to the code they're submitting.

      The reason you don't have to look at assembly is that the .c file is essentially a 100% reliable and unambiguous spec of how the assembly will look like, and you will be generating the assembly from that .c file as a part of the build process anyway. I don't see how this works here. It adds a lengthy artifact without lessening the need for a code review. It may be useful for investigations in enterprise settings, but in the OSS ecosystem?...

      Also, people using AI coding tools to submit patches to open-source projects are weirdly hesitant to disclose that.

    • WD-42 an hour ago

      This is only true if a llm session would produce a deterministic output which is not the case. This whole “LLMs are the new compiler” argument doesn’t hold water.

    • sumeno an hour ago

      cc was deterministic, you could be confident that the same code produced the same assembly each time you ran it

      That is very much not the case with LLMs

    • ehnto an hour ago

      LLMs are non-deterministic, you would end up with a different output even if you paste the same conversation in. Even if the model was identical at the time you tried to reproduce it. Which gets less likely as time passes.

      Also, why would you need to reproduce it? You have the code. Almost any modification to said code would benefit from a fresh context and refined prompt.

      An actual full context of a thinking agent is asinine, full of busy work, at best if you want to preserve the "reason" for the commits contents maybe you could summarise the context.

      Other than that I see no reason to store the whole context per commit.

  • rcy an hour ago

    I haven't adopted this yet, but have a feeling that something like this is the right level of recording the llm contribution / session https://blog.bryanl.dev/posts/change-intent-records

    • 4b11b4 34 minutes ago

      I like it, but it seemed test could capture some of these "behaviors". But having it in a single document is helpful for context

  • travisgriggs an hour ago

    In our (small) team, we’ve taken to documenting/disclosing what part(s) of the process an LLM tool played in the proposed changes. We’ve all agreed that we like this better, both as submitters and reviewers. And though we’ve discussed why, none of us has coined exactly WHY we like this model better.

  • jiveturkey an hour ago
    • reg_dunlop an hour ago

      Thank you! Was looking for this company. Founder was high up at GitHub. Really an interesting proposition

  • spion an hour ago

    A summary of the session should be part of the commit message.

  • danhergir 3 hours ago

    One of the use cases i see for this tool is helping companies to understand the output coming from the llm blackbox and the process which the employee took to complete a certain task

    • tartoran an hour ago

      Why do that? Just let them deal with it.

  • lsc4719 an hour ago

    Proof sketch is not proof

  • foamzou an hour ago

    No. Prompt-like document is enough. (e.g. skills, AGENTS.md)

  • hsuduebc2 an hour ago

    I must say that would certainly show some funny converstaions in a log.

  • ares623 3 hours ago

    Maybe Git isn't the right tool to track the sessions. Some kind of new Semi-Human Intelligence Tracking tool. It will need a clever and shorter name though.