Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The quality of AI-assisted software depends on unit of work management

blog.nilenso.com

Post reply on HN
Print view View original

41–50 of 127 posts

Re: The quality of AI-assisted software depends on unit of work management

#41

Post by marstall »

doing things in small chunks is good. so is it doing things in large chunks sometimes. In AI, like in life, there are no hard and fast rules and we're all figuring it out as we go. Like with "vibe coding" - sometimes it's ok to not even look at the code AI is generated, sometimes you need to understand every line.

It feels like part of my journey to being an "AI developer" is being present for those tradeoffs, metabolizing each one into my craft.

AI is a fickle, but powerful horse. I'm finding it a privilege to learn how to be a rider.

Re: The quality of AI-assisted software depends on unit of work management

#42

Post by liszper »

pjc50 wrote: post #36
liszper wrote: post #22

Earlier quoted context omitted.

200k DAU, 7 million registered, ~50 microservices, large monorepo

.. what is this thing and can we see it?

you can OSINT me pretty easily, not going to post it here for the sake of anonymity against crawlers who train models on our conversations. today's HN comments are tomorrow's coding LLMs

Re: The quality of AI-assisted software depends on unit of work management

#43

Post by palmotea »

OptionOfT wrote: post #38

And the value of AI as pushed to us by these companies is in doing larger units of work. But... reviewing code is harder than writing code. Expressing how I want something to be done in natural language is incredibly hard. So over time I'm spending a lot of energy in those things, and only getting it 80% right. Not to mention I'm constantly in this highly suspicious mode, trying to pierce through the veil of my own p…

That makes very clear these tools are not meant to serve you, you are meant to serve these tools.

Re: The quality of AI-assisted software depends on unit of work management

#44

Post by smw »

tedggh wrote: post #35

I found out that summarizing a completed task and feeding it to a new context works better than staying on the same context for multiple tasks. So let’s say I have a sprint with tasks 1, 2 and 3. I start by creating a project with general information including the spec, git issues, code base, folder trees, etc then work on Task 1. When done I ask for a summary using a template, which gives me a txt file describing wh…

Hell, claude even makes that part of the standard workflow, with /compact; cleverly using the llm itself to summarize the previous context

Re: The quality of AI-assisted software depends on unit of work management

#45

Post by BinaryIgor »

datadrivenangel wrote: post #2

Keep your scope as small as necessary, but no smaller. This has been fundamentally true for project management work breakdown structures for decades.

Interesting that it turns out to be true for code generation as well!

Re: The quality of AI-assisted software depends on unit of work management

#46

Post by bluefirebrand »

angusturner wrote: post #15
liszper wrote: post #3

most SWE folks still have no idea how big the difference is between the coding agents they tried a year ago and declared as useless and chatgpt 5 paired with Codex or Cursor today thanks for the article, it's a good one

I think most SWEs do have a good idea where I work. They know that its a significant, but not revolutionary improvement. If you supervise and manage your agents closely on well scoped (small) tasks they are pretty handy. If you need a prototype and don't care about code quality or maintenance, they are great. Anyone claiming 2x, 5x, 10x etc is absolutely kidding themselves for any non-trivial software.

> If you supervise and manage your agents closely on well scoped (small) tasks they are pretty handy

Compared to just doing it yourself though?

Imagine having to micromanage a junior developer like this to get good results

Ridiculous tbh

Re: The quality of AI-assisted software depends on unit of work management

#47

Post by bluefirebrand »

bubblyworld wrote: post #37
abtinf wrote: post #8

Earlier quoted context omitted.

liszper: > most SWE folks still have no idea how big the difference is between the coding agents they tried a year ago and declared as useless and chatgpt 5 paired with Codex or Cursor today Also liszper: oh, you tried the current approach and don’t agree with me? Well you just don’t know what you are doing.

Lol, what is up with everyone assuming there's no learning curve to these things? If you applied this argument to literally any other tool you would be laughed at, for good reason.

Probably because "there's no learning curve they are just magic tools" is how they are marketed and how our managers are expecting them to work

Re: The quality of AI-assisted software depends on unit of work management

#48

Post by furyofantares »

smw wrote: post #44
tedggh wrote: post #35

I found out that summarizing a completed task and feeding it to a new context works better than staying on the same context for multiple tasks. So let’s say I have a sprint with tasks 1, 2 and 3. I start by creating a project with general information including the spec, git issues, code base, folder trees, etc then work on Task 1. When done I ask for a summary using a template, which gives me a txt file describing wh…

Hell, claude even makes that part of the standard workflow, with /compact; cleverly using the llm itself to summarize the previous context

/compact is really poor imo. Quality just falls off a ledge after it.

I much prefer to choose tasks that can be done with 25%+ context left and then just start the next task with fresh context.

If I'm getting low on context I have it summarize the plan and progress in a text file rather than use /compact and then start a fresh context and reference that file, which I can then edit and try again if I'm not getting good results.

Re: The quality of AI-assisted software depends on unit of work management

#49

Post by ryoshu »

palmotea wrote: post #43
OptionOfT wrote: post #38

And the value of AI as pushed to us by these companies is in doing larger units of work. But... reviewing code is harder than writing code. Expressing how I want something to be done in natural language is incredibly hard. So over time I'm spending a lot of energy in those things, and only getting it 80% right. Not to mention I'm constantly in this highly suspicious mode, trying to pierce through the veil of my own p…

That makes very clear these tools are not meant to serve you, you are meant to serve these tools.

Reverse centaur.

Re: The quality of AI-assisted software depends on unit of work management

#50

Post by nicce »

OptionOfT wrote: post #38

And the value of AI as pushed to us by these companies is in doing larger units of work. But... reviewing code is harder than writing code. Expressing how I want something to be done in natural language is incredibly hard. So over time I'm spending a lot of energy in those things, and only getting it 80% right. Not to mention I'm constantly in this highly suspicious mode, trying to pierce through the veil of my own p…

> Expressing how I want something to be done in natural language is incredibly hard

Surprise, surprise… that is why programming languages were created.

Post reply on HN