←back to thread

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

(blog.nilenso.com)
170 points mogambo1 | 1 comments | 18 Sep 25 13:06 UTC | HN request time: 0.001s | source
Show context
liszper ◴[18 Sep 25 13:55 UTC] No.45289744[source]▶
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

replies(7): >>45289898 #>>45289951 #>>45289959 #>>45290163 #>>45290198 #>>45290340 #>>45290435 #
angusturner ◴[18 Sep 25 14:29 UTC] No.45290163[source]▶
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.

replies(5): >>45290226 #>>45291330 #>>45291991 #>>45292788 #>>45294931 #
dingnuts ◴[18 Sep 25 16:54 UTC] No.45291991[source]▶
if the benefit is less than 2x then we're talking about AI assisted coding as being a very, very expensive IntelliSense. 1.x improvement just isn't much. My mind goes back to that study showing engineers claimed a 20% improvement and measured 20% reduction in productivity -- this is all encouraging me to just keep using traditional tools.
replies(1): >>45298056 #
1. rmunn ◴[19 Sep 25 04:49 UTC] No.45298056[source]▶
The only AI-assisted software work I've seen actually have a benefit is the way my coworker use Supermaven, where it's basically Intellisense but suggesting filling in the function parameters for you as well. He'll type `MergeEx` and it will not just suggest `MergeExample(` as Intellisense would have done, but also suggest `MergeExample(oldExample, newExample, mergeOptions)` based on the variable names in scope at the moment and which ones line up with the types. Then he presses Tab and moves on, saving 10-15 seconds of typing. Repeat that multiple times through the day and it might be a 10% improvement, with no time lost on fiddling with prompts to get the AI to correct its mistakes. (Here, if the suggestion is wrong, he just ignores it and keeps typing, and the second he types a character that wasn't the next one in the suggestion it goes away and a new suggestion might be calculated, but the cognitive load in ignoring the incorrect suggestion is minimal).