News for hackers. Stuff that matters.
Re:Home-Cooked Software and Barefoot Developers by llm_trw on Tuesday June 11, 2024 @08:46PM (#40653309)
>Depending on the way you phrase questions, ChatGPT will gleefully suggest you a wrong approach, just because it’s so intent on satisfying your whim instead of saying No when it would be appropriate.

Which is easily solved by using another agent that is told to be critical and find all flaws in the suggested approach.

Re:Home-Cooked Software and Barefoot Developers by theamk on Tuesday June 11, 2024 @09:11PM (#40653450)
Not likely.

Have you seen AI code review tools? They are just as bad as any other AI products - it has a similar chance of fixing a defect or introducing a new one.

Re:Home-Cooked Software and Barefoot Developers by llm_trw on Tuesday June 11, 2024 @09:47PM (#40653665)
They are not there to fix defect, they are there to detect them.
Re:Home-Cooked Software and Barefoot Developers by theamk on Tuesday June 11, 2024 @10:37PM (#40653924)
Sure, but it's LLM - so this would be mix of some of the real defects (but not all of them) and a totally fake defects which do not actually need fixing. This is not going to help junior developers figure out good from bad.
Re:Home-Cooked Software and Barefoot Developers by llm_trw on Wednesday June 12, 2024 @02:49AM (#40655322)
And by running multiple versions of the system in parallel you can have them vote on which is the most likely part of the code which is a bug and which isn't.

We've known how to make reliable components out of unreliable ones for a century now. LLMs aren't magic boxes which make all previous engineering obsolete.

Re:Home-Cooked Software and Barefoot Developers by TeMPOraL on Wednesday June 12, 2024 @03:28AM (#40655515)
> this would be mix of some of the real defects (but not all of them) and a totally fake defects which do not actually need fixing

... and real defects that you never noticed or would've thought of.

> This is not going to help junior developers figure out good from bad.

Neither is them inventing fake defects which do not actually need fixing on their own. What helps juniors is the feedback from more senior people, as well as reality itself. They'll get that either way (or else your whole process is broken, and that has zero to do with AI).