←back to thread

AI’s coding evolution hinges on collaboration and trust

(spectrum.ieee.org)
183 points WolfOliver | 1 comments | 29 Aug 25 15:24 UTC | HN request time: 0.217s | source
Show context
UncleEntity ◴[29 Aug 25 16:38 UTC] No.45066292[source]▶
> These kinds of complex tasks can be difficult for AI development tools to navigate, resulting in hallucinations about where the bug is or its root cause, as well as irrelevant suggestions or code fixes with subtle problems.

How is this any different than the way I program?

I've contributed genuinely useful features to FLOSS projects "as well as irrelevant suggestions or code fixes with subtle problems", mostly the latter as there was always a few stages of improvement and/or finishing by the core devs of the program I used to haunt. Honestly, I was less than half as useful as the current crop of robots and they still tolerated (in fact, encouraged) my involvement.

replies(1): >>45066542 #
1. arscan ◴[29 Aug 25 16:56 UTC] No.45066542[source]▶
> Honestly, I was less than half as useful as the current crop of robots and they still tolerated (in fact, encouraged) my involvement.

Don’t sell yourself short. External contributors are extremely valuable as they are often users and provide real world validation of a need for whatever they are contributing. They also retain any knowledge for any feedback they receive that they can apply to future contributions. And they also become advocates for that software, helping it grow its user base.

LLMs, not so much.