I know a few very serious and well compensated programmers with decades of experience. These people work on prominent open source projects, climate modelling, linear programming, large org enginneering. Every single one of them uses LLMs heavily and swears by the increased productivity of using them.
Maybe that's true, I don't know. I make no claims of an unbiased sample. Merely a counterfactual to the parent comment's claim that they aren't useful.
I find the opposite. A good engineer would tell the agent the "know what they know they're doing" part. Let the AI take that direction and context, let it implement/test it 100x faster than a human can by hand, the engineer come back and confirm AI did the job about the same way as they would have wanted it to be done themselves.
> for an engineer who knows what he's doing, LLMs are of very limited use
LLMs are very good at code analysis, and finding both security issues and optimization opportunities. Yes, even in code written by highly experienced human engineers. Failing to have an LLM look for places where your code could be optimized is, IMHO, indefensible. It's like shipping your binaries compiled at -O0 - deliberately choosing to waste your users' time and hardware resources because you couldn't be bothered to properly configure and run a tool.
Code has never been the bottleneck for a skilled engineer, and if you value high quality then you need to spend a lot of time reading over the slop LLMs produce to turn it into something hardened and reliable. So, for a skilled engineer, LLMs have a very marginal benefit in terms of delivery speed.
I think there is some nuance to this. As a self-identified skilled engineer, most or what i -actually do- is not bottlenecked by writing code. However, there is a lot of stuff that I pre-LLM -didn’t do- because it was medium value and high effort. There is a class of work that is now zero effort to have an LLM generate, still medium value, and crucially low effort to validate.
I’m not sure this is a large class of work created in the long run, but since this efficiency is new, our backlogs are full of these tasks, and people are feeling immense efficiency gains from unlocking them.
They literally just shipped a massive update for a game they've been developing for several years (Deadlock) and are releasing more content for it this Friday
Do you think Deadlock will not devolve into a mixture of gambling and hvh like every Valve multiplayer game that’s been relevant in the last 10 years (except Dota because hvh in dota sounds complex, so it's just gambling there)?
Fortnite avoids this by having no gambling and by making hvh infeasible FYI
Every Valve game utilizing this is rated M. Control your children better instead of blaming others for being a bad parent. If you children have money to gamble and you let them play mature-rated games then you are doing it wrong.
I don't see why not. They clearly know what they are doing at Valve, and for an engineer who knows what he's doing, LLMs are of very limited use.