Most active commenters
  • CuriouslyC(3)

←back to thread

Some thoughts on LLMs and software development

(martinfowler.com)
416 points floverfelt | 11 comments | 28 Aug 25 18:52 UTC | HN request time: 0.001s | source | bottom
Show context
nicwolff ◴[28 Aug 25 21:18 UTC] No.45057148[source]▶
> I’ve often heard, with decent reason, an LLM compared to a junior colleague.

No, they're like an extremely experienced and knowledgeable senior colleague – who drinks heavily on the job. Overconfident, forgetful, sloppy, easily distracted. But you can hire so many of them, so cheaply, and they don't get mad when you fire them!

replies(11): >>45057296 #>>45057327 #>>45057402 #>>45058005 #>>45058021 #>>45058031 #>>45058066 #>>45058320 #>>45058354 #>>45059469 #>>45060122 #
furyofantares ◴[28 Aug 25 21:44 UTC] No.45057402[source]▶
These metaphors all suck. Well, ok, yours is funny. But anyway, LLMs are just very different from any human.

They are extremely shallow, even compared to a junior developer. But extremely broad, even compared to the most experienced developer. They type real fuckin fast compared to anyone on earth, but they need to be told what to do much more carefully than anyone on earth.

replies(5): >>45057580 #>>45057833 #>>45059467 #>>45059884 #>>45060020 #
1. CuriouslyC ◴[28 Aug 25 22:38 UTC] No.45057833[source]▶
I've gotten Claude Code to make CUDA kernels and all kinds of advanced stuff that there's zero percent chance a junior would pull off.

AI is like a super advanced senior wearing a blindfold. It knows almost everything, it's super fast, and it gets confused pretty quickly about things after you tell it.

replies(4): >>45058215 #>>45058307 #>>45058506 #>>45059628 #
2. skeeter2020 ◴[28 Aug 25 23:32 UTC] No.45058215[source]▶
it's not a senior though, because of the amount of oversight and guidance required. I trust senior-plus human developers to do the right thing and understand why it's the right thing. For mission critical things I get another human senior to verify. There's no way I'd autonomously trust 2, 10 or any number of LLMs to do the same thing.
3. QuadmasterXLII ◴[28 Aug 25 23:46 UTC] No.45058307[source]▶
have you ever asked a junior developer to write a cuda kernel?
replies(1): >>45058350 #
4. CuriouslyC ◴[28 Aug 25 23:53 UTC] No.45058350[source]▶
I've asked juniors to write easier things without success, and I applied the transitive property.
replies(1): >>45058988 #
5. achierius ◴[29 Aug 25 00:15 UTC] No.45058506[source]▶
You'd be surprised at what juniors can pull off. I have seen fresh-out-of-college new grads write performant GPU kernels that are used in real world library implementations for particular architectures.
replies(3): >>45058552 #>>45058560 #>>45060958 #
6. computerex ◴[29 Aug 25 00:22 UTC] No.45058552[source]▶
What's your sample size?
7. CuriouslyC ◴[29 Aug 25 00:23 UTC] No.45058560[source]▶
Most of the juniors I've worked with would make numerical errors and give up/declare premature victory before getting the implementation to a robust state. I'm sure there are exceptional young folks out there though.
replies(1): >>45059938 #
8. ◴[29 Aug 25 01:28 UTC] No.45058988{3}[source]▶
9. andoando ◴[29 Aug 25 02:57 UTC] No.45059628[source]▶
And today I asked Claude code to carefully look at and follow the structure of my tests and write some more, and after 5-10 mins it completely ignored it, wrote one class with all the helper methods and a bunch of compilation errors from fields that arent even in my model.

I figured there's probably a ton more logical issues and deleted it immediately

10. godelski ◴[29 Aug 25 03:47 UTC] No.45059938{3}[source]▶

  > Most of the juniors
Most senior programmers can't write CUDA kernels either. Even fewer can write ones that are any good.
11. versteegen ◴[29 Aug 25 06:42 UTC] No.45060958[source]▶
Of course they can. It doesn't take that long to learn CUDA/etc and hardware details, read through some manuals and performance guides, do some small projects to solidify that knowledge. What you need is talent, and some months. That's why at university I saw plenty of students pull off amazing projects, and there's nothing eyebrow-raising in the slightest about starting a PhD a year after getting a bachelor's and writing software more sophisticated than most programmers would write in their career.

I think the programming profession overvalues experience over skill. However, when I was young I had no appreciation for what the benefits of experience are... including not writing terrible code.