News for hackers. Stuff that matters.
Re:We stopped roadmap work for a week and fixed 189 bugs by ChrisMarshallNY on Monday November 24, 2025 @12:31AM (#46030675)
Yes. I often just copy the whole core dump, and feed it into the prompt.
Re:We stopped roadmap work for a week and fixed 189 bugs by Lionga on Monday November 24, 2025 @02:01AM (#46031149)
And this kids is how one bug got fixed and two more were created
Re:We stopped roadmap work for a week and fixed 189 bugs by ChrisMarshallNY on Monday November 24, 2025 @05:05AM (#46032297)
Nope.

Good result == LLM + Experience.

The LLM just reduces the overhead.

That’s really what every “new paradigm” has ever done.

Re:We stopped roadmap work for a week and fixed 189 bugs by enraged_camel on Monday November 24, 2025 @09:19AM (#46034385)
Also, robust test coverage helps prevent regressions.
Re:We stopped roadmap work for a week and fixed 189 bugs by Sohcahtoa82 on Monday November 24, 2025 @12:58PM (#46036963)
There's a huge difference between using an LLM to assist you versus letting it just do all the work for you. Your implication that they're the same, and that the previous commenter let the LLM do the work, is lazy.

ChrisMarshallNY only said they fed the dump into the LLM. They said nothing about using the LLM to write the fix.

Re:We stopped roadmap work for a week and fixed 189 bugs by criddell on Monday November 24, 2025 @09:49AM (#46034737)
This is something that I've been trying to improve at. I work on a Windows application and so I get crash dumps that I open with WinDbg and then I usually start looking for exceptions.

Is this something an LLM could help with? What exactly do you mean when you say you feed a dump to the prompt?

Re:We stopped roadmap work for a week and fixed 189 bugs by ChrisMarshallNY on Monday November 24, 2025 @10:43AM (#46035322)
I literally copy the whole stack dump from the log, and paste it into the LLM (I find that ChatGPT does a better job than Claude), along with something along the lines of:

> I am getting occasional crashes on my iOS 17 or above UIKit program. Given the following stack trace, what problem do think it might be?

I will attach the source file, if I think I know the general area, along with any symptoms and steps to reproduce. One of the nice things about an LLM, is that it's difficult to overwhelm with too much information (unlike people).

It will usually respond with a fairly detailed analysis. Usually, it has some good ideas to use as starting points.

I don't think "I have a bug. Please fix it." would work, though. It's likely to try, but caveat emptor.

Re:We stopped roadmap work for a week and fixed 189 bugs by int_19h on Monday November 24, 2025 @11:16PM (#46042288)
I kinda wonder if at some point this is something we might use the LLM more directly for. As in, train them on raw binary dumps as input.
Re:We stopped roadmap work for a week and fixed 189 bugs by ChrisMarshallNY on Tuesday November 25, 2025 @12:34PM (#46048257)
I wonder if we’ll be seeing tools that do this.

I could see Apple or Microsoft, building it into their IDEs.

But, as was noted elsewhere, I think it’s only useful as an advisor. I think a lot of folks look at LLMs as some kind of programmer replacement.

Re:We stopped roadmap work for a week and fixed 189 bugs by wahnfrieden on Tuesday November 25, 2025 @12:59PM (#46048596)
They are that too
Re:We stopped roadmap work for a week and fixed 189 bugs by ChrisMarshallNY on Tuesday November 25, 2025 @03:06PM (#46050090)
I still wouldn't trust them for a lot of stuff.

Some of the code I get from Claude and ChatGPT is ... not so good.

Re:We stopped roadmap work for a week and fixed 189 bugs by wahnfrieden on Tuesday November 25, 2025 @05:11PM (#46051421)
I review it and I sometimes have it retry the same task 40+ times
Re:We stopped roadmap work for a week and fixed 189 bugs by int_19h on Wednesday November 26, 2025 @12:00PM (#46059581)
It's like an intern that is incapable of learning. But a very enthusiastic one.