63 comments

  • frostiness 4 hours ago ago

    I don't know if I'm doing something wrong but bug fixing with AI has always been a crapshoot. You can absolutely tell an agent to fix an issue, and it will fix that issue, but the vast majority of the time that solution will be by adding code to cover the specific symptom in the bug report. It rarely considers or recommends solutions that have tradeoffs that may change behavior but will eliminate an entire class of similar bugs.

    This is mostly a problem of agents not having the autonomy of managing an entire project and having the ability to make tradeoffs to increase simplicity or maintainability, but when given that autonomy no AI model I've used uses that privilege to write simpler, more maintainable code.

    • davnicwil 3 hours ago ago

      I think this gets to something quite fundamental which is in the information loss when delegating a task in plain English.

      It's very hard and actually a lot of work to draw an appropriate buffer around a problem in terms of how much agency you want to be exercised in considering other concerns when fixing it.

      It takes a lot of skill on both sides to negotiate this even in an ongoing conversational loop.

      There comes a point of course where essentially doing this communication and negotiation is equivalent to the work. At that point, you really aren't saving all that much time by not writing the code yourself in a lot of cases.

      Maybe greenfield type work is the exception, where generating the code can actually save hours of typing, but certainly for bugfixes on mature systems where the right fix with all factors and competing priorities considered and negotiated only results in say 10 lines of new code, you start to wonder what actually is the benefit of delegation and automation here.

    • tauwauwau 2 hours ago ago

      It should work, unless you're working on a very large codebase. I give the AI all the information that I would consider before implementing the solution, my prompts sometimes are multiple paragraphs, it's tedious but it gives good results. Information that I provide may include links to different repositories that may impact the feature being implemented, broad description of some terms, instructions to use a local temp/ directory to create temporary/reusable scripts when needed. Sometimes when I don't trust it, I explicitly ask it to come up with a plan without changing anything. Other times, I ask it to implement, build deploy, test deployed app and loop till the feature works. One of the instructions that I have in Agents.md is to periodically save session summaries in ./docs/ directory, you can use an external file. I haven't tried any context-management tools other than context-mode, which seemed to make it worse. But I haven't needed anything more than the docs/ directory yet, and that's when I leave it working for hours at a time to in implement/test/build/deploy loop. Interrupting it at every stage is going to make it slow, so it's better to see the end result and if you don't like the end result, you can try again with new instructions.

    • WillPostForFood 3 hours ago ago

      * It rarely considers or recommends solutions that have tradeoffs that may change behavior but will eliminate an entire class of similar bugs.*

      Are you specifically asking it to do that? You can just point AI at a bug and say "fix" or you can ask it to review, plan, offer alternatives. You can get a lot more out of it if you actively engage.

    • ex-aws-dude 3 hours ago ago

      It makes me wonder if it could be solved with better context management

      A real developer builds up global context of the whole project over time, you always hold the overall architecture in your head

      Whereas with agents there is a still a lot lost between sessions

      Its similar in a sense that a new developer to a project does more hacky local solutions whereas the senior on the team knows when the architecture needs to change as part of a fix

      • user43928 3 hours ago ago

        I think it's rather a problem with the training pipeline incentivizing correctness and endlessly defensive code over simplicity and maintainability of the implementation.

        The problem with context I see primarily in mixing up user intent and hard requirements with random half-correct notes some other agent left in the comments.

      • Unproven4275 2 hours ago ago

        > Whereas with agents there is a still a lot lost between sessions

        Are y'all using AI agentic frameworks? I don't have a lot of issue with anything being lost between sessions, I have active memory and context management and have my agents write up documentation for each project to pick up where they left off or to hand it off if needed.

      • philipwhiuk 3 hours ago ago

        > It makes me wonder if it could be solved with better context management

        There's a reason that repos are now bloated with AGENTS.md files that try to cram context in as pre-text. And that there's so many vibe-coded context/memory aggregation frameworks.

        It's an AI-hard problem.

    • Unproven4275 3 hours ago ago

      I mean I also think it's the way you prompt it.

      Whenever I bug fix, I prompt it specifically to solve the problem not fix the symptom of the problem, and do so with the least amount of code changes possible to fix the problem. And I also tell it that if there's a more maintainable way to solve the problem(like prevent similar issues in other parts of the project, ie problems with a particular dependency or library being used) to suggest alternatives.

      I think it's also important that the AI either has context to your entire project(like ability to read the source), or you put the context of what it's solving in the prompt you give it specifically.

      • frostiness 2 hours ago ago

        Neither of these prompts effectively address the problem though. Fixing the root cause and doing so with the least amount of code often is contradictory. Including instructions to make suggestions to improve code maintainability will cause the AI to do it every single time it makes a change, even if it's completely unnecessary, drowning out useful suggestions in noise. When a bug is caused by a requirement elsewhere in the application, current models are more likely to break that functionality and implement a fix anyway rather than pause and get confirmation on the requirement. They may leave a note about the broken functionality at the end, but by that point the AI has already been iterating with an incorrect assumption. Any code the agent wrote in the same turn is going to be tainted by that assumption and it often does not remove or rewrite that code when given clarified requirements.

        It's tempting to blame all AI issues on prompting because it's the only thing that we're able to control, but if a task falls into the long tail of work unable to be satisfactorily completed with AI, there's no prompt that will work. When there's always the alternative of doing the work yourself, it's not worthwhile to spend the tokens or time to get an AI model to do something after the first two or three prompts.

  • td521534f12 3 hours ago ago

    All my solo project backlogs _are_ empty.

    For my team projects, I still need my teammates to review code, so that bottlenecks how quickly we can burn down the backlog. If I didn't need code review I would have the backlog burned down in weeks, but I'd create a bunch of outages in the process (we do catch things in code review!)

    Also, some of my solo projects are gamedev-related, and gamedev is also bottlenecked on actually playing your game to see if its fun :) but it is great to get out of a 2 hour playtest session with notes and have a new build in like 15 minutes with the feedback incorporated.

    • bestouff 3 hours ago ago

      I was going to say that. Solo projects advance fast now, and bugs are very few.

      • sockaddr 2 hours ago ago

        Bugs on your solo project are not few. They are merely undiscovered because the bug detection is bottlenecked on you.

        • klik99 2 hours ago ago

          Exactly this

          I read something recently that devs don’t know how good frontier models are, and that only researchers can really see that programming is solved. I’ll believe it when one of those people makes an app / product used by hundreds of thousands of people without constant downtime and regressions. Microsoft hasn’t been able to.

          I mean it’s magic for things that don’t require maintenance or handling edge cases of significant number of users (math proofs are a great example of how magic it can be), or finding the root causes of bugs, and it’s a great tool. But it’s not a magic fix all, at least right now. I’m fine with people speculating it will be, but constantly annoyed at how people conflate what might be with what is right now.

      • risyachka 3 hours ago ago

        Feel free to share the product if there are really so few bugs

        • _jss 3 hours ago ago

          I am building Flightpad (https://flightpad.net) and absolutely wouldn't without AI tools.

          I have several validation loops that run full test harnesses over live (and ever-changing) data. AI brings some subjective evaluation, since data output is all deterministic there are bugs that pop up.

          My bug list is nearly empty always. It takes some focus to solve a lot of the data bugs, because I need to understand the root causes (or I feel I need to).

          AI has been an incredibly useful addition to my solo work.

        • Olscore 3 hours ago ago
    • beebmam 2 hours ago ago

      Humans should not be the bottleneck to shipping code; verification systems should be.

      • td521534f12 2 hours ago ago

        My day job is in a regulated industry, we are required to have humans review everything. WE do have many many thousands of tests verifying behaviors, linters, autoformatting, we can get agents for an extra review, but human review is not going away in my industry for a long time.

  • fishtoaster 3 hours ago ago

    It pretty much is? Every easily-described bug has been fixed. The only things that remain are "this isn't wrong per se, it just violates customer expectations" and someone needs to figure out what the product should do in this case.

    We burnt through our backlog of "obviously we should do this when we have time" stuff in the spring. It was pretty fun to kill pretty much all of my multi-year refactor and cleanup list.

    Now we are pretty much bottlenecked on the business side.

    • coffeebeqn an hour ago ago

      Our bug backlog is also practically empty (backend, financial). It’s a bit more slow moving and low bug domain for us in general but still. I went looking the other day and all that’s left is some dependency updates and such. I don’t know what models you guys are using if it can’t fix most bugs pretty easily with a decent set of steps defined

      • ex-aws-dude an hour ago ago

        Let me give you an example

        According to our metrics there is a crash in the wild that occurs 1 in 10000 launches of the product (desktop C++ app), all we have is a lightweight crash dump with call stack

        I put Opus 5.5 on it and it spins and spins and comes back with some theories, some sound convincing but I can't test them as no one can reproduce the bug (tricky timing or some unknown combination of states)

        Eventually I submit one as a speculative fix and it comes back in a few days that the crash is still occurring

        I would love to just aim the agent at it and get a fix but it just doesn't happen a lot of times

  • davesmylie an hour ago ago

    I'm in devops, not programming, so slightly different.

    I can say our backlog of absolutely essential jobs that we haven't been able to get around to for the last 5 years is absolutely being smashed out one by one. A lot of this is unattended server migrations running over night being validated the next day.

    The backlog as a whole though is growing as we have AI continually probing the infrastructure and various code bases looking for new security concerns or ways to improve performance and save money. Directly as a result of this, our cloud costs dropped massively in the last 6 months with only very minimal impact on performance.

    I absolutely see a time in the not too distant future where all our infrastructure tech debt has been cleaned up, the security situation is as good as we can get it, the backlog has completely emptied and some of my team will be surplus to requirements.

  • nzach 3 hours ago ago

    AI only can improve velocity if it mostly works unsupervised. But most people don't trust their agents to run alone.

    And to build that trust will take some time, people will need to learn how to use AI effectively.

    I think the PS3 hardware could be a good analogy. It was really powerful, but nobody really knew how to use it. After a few years people got really good at it . And you can view this evolution by the improvement of graphical fidelity we got over the years.

    • malfist 3 hours ago ago

      I'm not sure how you can claim it takes time to build trust with AI as if AI isn't actively demonstrating every day why it can't be trusted. Just this morning I had it review clinical notes from a procedure I had done and it mathed things wrong (declaring an injection was 2.5ml when it was 2ml of one thing plus 1ml of another).

      I ask it to fix one bug and it introduces three more. I ask it to add a feature and it adds four features.

      It has very little common sense. I asked it to build a feature that required api calls to openai, and it decided the best approach was to hand roll the interface code with some bonkers defaults (explicitly zero retries, explicit 1 second timeouts to non steaming api) and wrote the most fragile code that didn't generally work. Even when directed to use the published library by openai it still tried to apply its insane invited requirements to make even that fragile.

      I don't think it's nobody knows how to use it, its just not that reliable.

      • nzach 40 minutes ago ago

        > declaring an injection was 2.5ml when it was 2ml of one thing plus 1ml of another

        Maybe you could write a custom tool to give your agent to help him with these tasks they seem to struggle?

        Sometimes even a simple instruction in the AGENTS.md file can solve some problems.

        And another way to improve is to split task into easier ones (first create a csv with all injections then create a summary from that csv). The main tradeoff with this approach is that takes more time, but it can improve your reliability.

        I agree with you sentiment that these tools are pretty unreliable. But my approach is generally along the lines of 'how do I use something unreliable to do real work?'. All tools have limitations, and as an engineer I'm always trying to find ways to do more despite the limitations.

      • dagss 2 hours ago ago

        What model are you using/complaining about? Just seems so very removed from my work day where I am more usually impressed about the amount of common sense displayed by the AI..

        • IsTom 2 hours ago ago

          I find it to be very random. Sometimes it'll do something very reasonable on its own that solves a problem I haven't considered and then give up and say it's very hard when prompted to do the same in another project. Or it'll start adding some static HTTP headers somewhere deep in sever code instead of one line in apache config. And I'm mostly using Opus 5.5 on medium.

        • malfist an hour ago ago

          Generally using Astra at medium or high reasoning levels. Not that it matters, I see the same behavior in opus.

    • aDyslecticCrow 3 hours ago ago

      > can improve velocity if it mostly works unsupervised.

      I would refute that a bit. I've found quite a nice workflow using a small dumb model (haiku mostly), and basically use it as editor tooling. Change function signature here, split out section into a function and update all similar usage locations there, add a new file and update the make system over there. Trivial tasks that just takes longer to write myself; things i would trust are mostly correct because it still compiles.

      It's not a 10x workflow, but keeps me enjoying the coding without loosing track or stagnating my own learning. "commit this" is probably my most used prompt at this point. (with a few strict commit hooks to make it behave and keep brevity).

      Mabie a 50% velocity bump to the coding itself on a good day.

  • KronisLV 2 hours ago ago

    > The bug backlog should be empty

    Yup, I actually achieved that for a smaller system at work.

    Tracked down and resolved every single logged bug there, alongside additional correctness improvements - after migrating the system from Oracle to PostgreSQL (it had a narrow enough domain where that was possible, made iterating way easier due to how easy it is to work with PostgreSQL and tune its setup for a specific workload), adding Testcontainers and pushing the test coverage to the high 90s percent, as well as migrating the front end from Vue 2 to Vue 3. Also wrote a custom load testing tool and improved the performance by up to 20x (though there were some really bad querying and N+1 issues at play).

    It wasn't completely smooth and did create a few bugs along the way which also needed to be fixed, but overall was pretty solid - mostly due to the fact that the system had been developed with support for mock data from day 1 where you could spin up an instance and play around with pretty much anything you wanted. Hell, one could probably do a Rust rewrite of it if they didn't have anything better to do (not a Rust shop though).

    That approach wouldn't really work for larger systems as is (e.g. there are some that are like around half a million SLoC), underdocumented systems, or systems where testing is contrived and difficult, as well as some stacks that just suck (e.g. bringing down a shared dev DB instance preventing N people from doing their work). Oh and also it took about an order of magnitude more tokens than would normally be given to your average dev.

    Right now in my circumstances the bottleneck doesn't actually seem to be creating changes/features, but rather deployment and shipping as well as configuration management (assuming you have clients that need release instructions). Oh and being able to sell new work packages. Either way, in general you need more tests and specs than you think you do.

  • lordnacho 2 hours ago ago

    Last year during the summer I had a bunch of things I wanted to do to improve on the trading system I was working on. A bunch of things that were mostly fiddly, which I had estimated would take me 6 months.

    Someone told me to try out Claude Code during my holiday.

    I learned the backstory of Sauron with a friend while getting the entire backlog cleaned up. Things worked, better and faster and more maintainable.

    Did I run out of things to do? Well, the firm I was with didn't know what they wanted built, so it was a lot of not getting anything done while waiting for them. But the things they had previously wanted, yes, they were done.

  • yokuze 3 hours ago ago

    > The bug backlog should be empty

    I don't follow.

    Maybe it's just me, but I've never worked at a company and on any substantial product that had an empty bug backlog. If a bug queue is empty, the product is either not used much (or not a priority), not tested well enough, or not monitored enough.

    I don't know that a world where AI has mostly replaced programmers is a world with an empty bug queue.

    While AI is reducing the _quantity_ of programmers needed in many cases, it is also an output multiplier for the remaining programmers, while often raising the bug-to-code ratio.

    AI has led to more output, more projects, and more bugs.

    • Grombobulous 3 hours ago ago

      Well, I think you just unintentionally made the same point the poster is making. If it's an output multiplier then it should also multiply the ability to fix bugs. Bugs should be just getting fixed in my sleep right?

  • fritzo 3 hours ago ago

    Parkinson's Law:

    "Work expands so as to fill the time available for its completion"

    https://en.wikipedia.org/wiki/Parkinson%27s_Law

  • saulpw 3 hours ago ago

    The VisiData backlog is basically empty: https://github.com/saulpw/visidata/issues

  • g051051 3 hours ago ago

    Because just like without LLMs, focus is on delivering new products and features, not on paying down technical debt.

  • aynyc 3 hours ago ago

    Mine is. I've been telling my senior managements that it's cheaper to rewrite stuff from scratch with AI then fix OLD products. They ate that up and everything we have now never reach v1.0 status.

  • cadamsdotcom 3 hours ago ago

    If you or your company has nothing to build it means they're out of ideas. And if they're out of ideas, they have too many people.

    That's not a place you want to get to.

    • jgalt212 3 hours ago ago

      There's always post-mature optimization to work on.

  • PeterStuer 2 hours ago ago

    On the project I am working on atm, I think I am averaging a net addition of around 50-200 production LoC per day. The system produces around 10x as much test-harness code (feature + regression). Planning/exploring takes about 1/4th of the time, coding 1/20th, documentation 1/10th and testing all the rest. Backlog has no known bugs, quite a few de-prioritized very niche edge cases that in theory could arise but never showed up in production, but still could be nice to haves, and plenty of new desired functionality. I'm sure I could go 10x faster, but I choose not to as this pace nicely balances cost, progress and keeping it under control for me.

  • getfacl 2 hours ago ago

    I'll go out on a limb here and say that if your bug backlog is currently deep it might be because of general disorganization. We've all seen shops where there are no standards other than ship something "on time" and the result is a spaghetti mess that only gets worse as time goes on. This is a management problem that AI doesn't fix.

  • hawkice 4 hours ago ago

    It is empty, for me and my team (I'm an engineering manager). We still have a support rotation but it's just so someone is aware they're supposed to respond to any alerts that come up.

    Edit: product doesn't have a deep backlog either. Usually we can only plan somewhere between a couple days and a month in advance. Major recent product launch so we are longest-horizon we have been for a while.

    • maxdo 3 hours ago ago

      I can confirm the same, backlog is sort of empty unless we try to attack a new domain, and that's usually a 2-3 month party, after that you need to almost imagine tasks. this really smells like end of backlog situation to me.

      You can calm yourself and say we can attack and move upstream, e.g. instead of using crm lets write our own crm, etc. But if everyone else is doing so, what is the end game lol

      • freshnode 3 hours ago ago

        Genuine question... How secure do you feel your job is, in that case? There's only so far that road goes, I imagine? I doubt your management are gonna buy you building a custom OS to run your custom CRM on...?

  • sjrd 3 hours ago ago

    My bug backlog has been empty [1] at each release for 5 years in a row. We did not need AI to get there.

    [1] https://github.com/scala-js/scala-js/issues?q=is%3Aissue+sta...

  • johnshahbazian 3 hours ago ago

    It's empty for all the projects I'm working on. Is your team just not putting in the time to fix them?

    • ex-aws-dude 2 hours ago ago

      I would say it comes down to 3 things together as a bottleneck

      1) The agent couldn't find a fix after spending multiple hours with it debugging. For example a very rare non-reproducible C++ crash. Or the person operating it got fed up with how long it was taking and just manually figured it out.

      2) The AI proposed a fix but people aren't comfortable just submitting it unless someone reviews and understands it to ensure there are no knock-ons.

      3) Even when it does find a fix, its still time consuming to operate the agent and feed it info/test. There are also token limits at my company so you can't just burn through things ad infinitum.

      Also in my case the product is a huge codebase and has millions of users you have to worry about breaking so maybe that plays into it.

      • johnshahbazian an hour ago ago

        1. That does sound difficult. Did the agent have access to C++ debugging tools? And was it the latest and greatest model?

        2. I understand, but that's an organization issue.

        3. Another organization issue, but also very understandable. It gets very expensive to let engineers just rip.

        The huge codebase is definitely an issue - is there documentation geared toward an agent that's designed to give it a quick overview of the architecture and locations of things so that it can look up code in separate areas quickly? Obviously the agent, on its own, will grep its way through the codebase, but giving it an innate understand of how everything is structured is often very helpful.

        Altogether it sounds more like the difficulty of a very large codebase with a difficult language and an org that's (rightfully) hesitant to go all in. The first can be mitigated, the second perhaps, and the third maybe one day.

  • johnfn 2 hours ago ago

    Because some bugs are underspecified, and the specification is the remaining work. For instance, "I can add the same meal to the meal catalog twice". That's a bug. But how do you solve it? Do you merge them? Do you error on the second attempt? Maybe you allow for two variations of the same meal? Once you specify the bug then you can toss it into an LLM and it's done. If you toss it into an LLM without doing that it might solve it in a way you don't like.

  • efficax 2 hours ago ago

    I feel like you could only ask this question if you don't really understand software development. If you're building features, you're building bugs. Nobody ever said AI produced bug free code. But it does make it possible to evaluate code extensively to find bugs before you ship it. I believe the code I'm shipping now has far fewer bugs than ever before, but bug free? I don't even know if that makes sense. it all depends on what ends up counting as a bug, in the end.

    • ex-aws-dude 2 hours ago ago

      You mean the bottleneck is bug discovery?

      I dunno I still run into cases where it couldn't find a fix but I do work in C++ which I think has trickier bugs

  • swader999 3 hours ago ago

    Performance, Defect rate, feature velocity (5x), cycle time on defects to prod are all at the best they've been on our 7 year LOB 1.5 million loc system. 3 devs/2 qa, 2 sme's. 200 paying customers, moves money so it has to work.

    First time in 3 decades I don't have any tech debt that I NEED to tackle. Customers can't keep up with us. We are considering new products/adjacent markets. Strangely, our competitors (about 5 serious ones) don't seem to be matching us.

  • seizethecheese 2 hours ago ago

    A hidden assumption in your question is that the ai tools themselves don't create bugs or new backlog items. This is false. Even with perfect AI tools, bugs would slip in because of imprecise specifications.

    There are many universes where the number of bugs grows faster with better agents.

  • francisofascii 2 hours ago ago

    Our users don't have enough feature requests at this point. I have to be diligent in generating new ideas, features, improvements, etc. for the projects I work on. Otherwise we would run out of work.

  • Kuyawa 2 hours ago ago

    Bug tracker is empty but todo list is full with things to work on and new features to add

    I haven't seen AI make a single mistake yet while coding my apps

  • guessmyname 3 hours ago ago

    My bug backlog is empty. My task backlog is not.

  • bearjaws 3 hours ago ago

    "Competitor X is working on Y, we need to beat them to it!"

    Thus Y is prioritized over bugs.

  • HoldOnAMinute 3 hours ago ago

    Even AI breaks things when trying to fix bugs.

  • sailorganymede 3 hours ago ago

    Standards are super low, so slop gets approved and no one is checking. We get graded on how many Jiras we close. A bug gets a Jira. So we are doing great!

    • phoghed 3 hours ago ago

      TIL Jira is fractal

  • andrewstuart 3 hours ago ago

    Scope creep scales, that’s why.