Newshot

Ask HN: If AI tools are so good, why isn't your bug backlog empty?

Original text(via Hacker News)
Ask HN: If AI tools are so good, why isn't your bug backlog empty?
21 points by ex-aws-dude 1 hour ago │ hide │ past │ favorite │ 17 comments
A lot of people outside tech ask me if AI is going to replace programmers and I just think: if that were the case we should be running out of things to do The bug backlog should be empty and we've caught up to every feature request from PMs to the point that we are bottlenecked on the business side But that does not seem to be the case with my own company or most devs I talk to in the industry So what gives?

The bug backlog should be empty and we've caught up to every feature request from PMs to the point that we are bottlenecked on the business side

But that does not seem to be the case with my own company or most devs I talk to in the industry

So what gives?

td521534f12 8 minutes ago │ next [–] 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. replytd521534f12 8 minutes ago │ next [–] 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. reply
td521534f12 8 minutes ago │ next [–] 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. reply
bestouff 4 minutes ago │ parent │ next [–] I was going to say that. Solo projects advance fast now, and bugs are very few. replybestouff 4 minutes ago │ parent │ next [–] I was going to say that. Solo projects advance fast now, and bugs are very few. reply
bestouff 4 minutes ago │ parent │ next [–] I was going to say that. Solo projects advance fast now, and bugs are very few. reply
risyachka 2 minutes ago │ root │ parent │ next [–] Feel free to share the product if there are really so few bugs replyrisyachka 2 minutes ago │ root │ parent │ next [–] Feel free to share the product if there are really so few bugs reply
risyachka 2 minutes ago │ root │ parent │ next [–] Feel free to share the product if there are really so few bugs reply
fritzo 4 minutes ago │ prev │ next [–] Parkinson's Law: "Work expands so as to fill the time available for its completion" https://en.wikipedia.org/wiki/Parkinson%27s_Law replyfritzo 4 minutes ago │ prev │ next [–] Parkinson's Law: "Work expands so as to fill the time available for its completion" https://en.wikipedia.org/wiki/Parkinson%27s_Law reply
fritzo 4 minutes ago │ prev │ next [–] Parkinson's Law: "Work expands so as to fill the time available for its completion" https://en.wikipedia.org/wiki/Parkinson%27s_Law reply
frostiness 49 minutes ago │ prev │ next [–] 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. replyfrostiness 49 minutes ago │ prev │ next [–] 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. reply
frostiness 49 minutes ago │ prev │ next [–] 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. reply
ex-aws-dude 23 minutes ago │ parent │ next [–] 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 replyex-aws-dude 23 minutes ago │ parent │ next [–] 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 reply
ex-aws-dude 23 minutes ago │ parent │ next [–] 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 reply
philipwhiuk 10 minutes ago │ root │ parent │ next [–] > 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. replyphilipwhiuk 10 minutes ago │ root │ parent │ next [–] > 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. reply
philipwhiuk 10 minutes ago │ root │ parent │ next [–] > 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. reply
nzach 9 minutes ago │ prev │ next [–] 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. replynzach 9 minutes ago │ prev │ next [–] 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. reply
nzach 9 minutes ago │ prev │ next [–] 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. reply
cadamsdotcom 13 minutes ago │ prev │ next [–] 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. replycadamsdotcom 13 minutes ago │ prev │ next [–] 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. reply
cadamsdotcom 13 minutes ago │ prev │ next [–] 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. reply
jgalt212 12 minutes ago │ parent │ next [–] There's always post-mature optimization to work on. replyjgalt212 12 minutes ago │ parent │ next [–] There's always post-mature optimization to work on. reply
jgalt212 12 minutes ago │ parent │ next [–] There's always post-mature optimization to work on. reply
sjrd 1 minute ago │ prev │ next [–] 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... replysjrd 1 minute ago │ prev │ next [–] 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... reply
sjrd 1 minute ago │ prev │ next [–] 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... reply
g051051 3 minutes ago │ prev │ next [–] Because just like without LLMs, focus is on delivering new products and features, not on paying down technical debt. replyg051051 3 minutes ago │ prev │ next [–] Because just like without LLMs, focus is on delivering new products and features, not on paying down technical debt. reply
g051051 3 minutes ago │ prev │ next [–] Because just like without LLMs, focus is on delivering new products and features, not on paying down technical debt. reply
johnshahbazian 11 minutes ago │ prev │ next [–] It's empty for all the projects I'm working on. Is your team just not putting in the time to fix them? replyjohnshahbazian 11 minutes ago │ prev │ next [–] It's empty for all the projects I'm working on. Is your team just not putting in the time to fix them? reply
johnshahbazian 11 minutes ago │ prev │ next [–] It's empty for all the projects I'm working on. Is your team just not putting in the time to fix them? reply
aynyc 27 minutes ago │ prev │ next [–] 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. replyaynyc 27 minutes ago │ prev │ next [–] 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. reply
aynyc 27 minutes ago │ prev │ next [–] 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. reply
hawkice 56 minutes ago │ prev │ next [–] 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. replyhawkice 56 minutes ago │ prev │ next [–] 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. reply
hawkice 56 minutes ago │ prev │ next [–] 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. reply
maxdo 14 minutes ago │ parent │ next [–] 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 replymaxdo 14 minutes ago │ parent │ next [–] 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 reply

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.

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

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

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.

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

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.

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.

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

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

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.

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

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by Hacker News
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗