News for hackers. Stuff that matters.
Re:Try Deep Think in the Gemini App by thunky on Saturday August 02, 2025 @08:54AM (#44767218)
> Even IF that were true (and I'd argue that it is NOT)

Can you share what these "hard problems" are that > 1% of developers are working on?

Re:Try Deep Think in the Gemini App by h4ch1 on Saturday August 02, 2025 @10:04AM (#44767735)
Try using any AI tool to write a working realtime GI (global illumination) implementation. I've been working on a novel implementation for 60fps/1080p GI and everytime I use Copilot or Claude to even try fixing a minor bug/troubleshoot it nukes entire functions and rewrites them using garbled shader code, old syntax/methods.

Puts things into stark perspective for me.

PS. no amount of prompt engineering will save you in this endeavour.

Re:Try Deep Think in the Gemini App by thunky on Saturday August 02, 2025 @02:09PM (#44769870)
> I've been working on a novel implementation for 60fps/1080p GI

I don't think this is the type of work a "normal" developer is working on though, which is what my question was targeting.

I would think 99%+ are going to use an existing implementation like unreal engine, which AI can certainly help with.

Re:Try Deep Think in the Gemini App by durumu on Monday August 04, 2025 @08:39AM (#44784991)
Even if most of the code you write is solving repetitive plumbing tasks, today's models are incredibly bad at API design taste. IMO designing software in a way that minimizes side effects and is easy to change and test is more than 1% of software engineering.

Lately most of the code I write has been through LLMs and I find them an enormous productivity booster overall, but despite the benchmarks they're not expert human level quite yet, and they need a LOT of coaxing to produce production quality code.

As far as things LLMs are bad at, I think it's mainly the long tail. I'm not sure there's one singular thing that >1% of programmers work on that LLMs suck at, but I think there are thousands of different weird sub-specialties that almost no one is working on and very little public code exists for, thus LLMs are not good at them yet.