Comment by eterm
15 hours ago
They're amazing at it, provided you keep asking the right questions.
Trust me when I say that in the hands of someone who doesn't have your experience, the LLMs would not be getting the results you get.
You might think what you're doing is trivial, it may be sessions that flow roughly, "Instrument this, okay this part is slow, profile this part, OK read the profile output and suggest a better approach".
But your experience will be steering it in the right direction, and you're probably unaware of just how much your experience is doing that guiding, as the LLM shoots off at 100mph, you feel like it's taking you with it, but you will be guiding it a lot more than you realise, and that's where learning and experience comes in, even if you're no longer operating at the lowest depth, your knowledge of that layer will be helping.
If nothing else, the experience to know when something is actually slow is a skill in itself. If a function takes 200ms, sometimes that's as quick as it can realistically go, and sometimes that's literally a million times slower than it could be, and there's actual skill and experience wrapped up in knowing what "slow" looks like.
> Trust me when I say that in the hands of someone who doesn't have your experience, the LLMs would not be getting the results you get.
https://code.ffmpeg.org/FFmpeg/FFmpeg/issues/23049
So there's this 11 year old issue in a forgotten ffmpeg plugin and I fixed it with deepseek by putting it into a self-testing loop. Probably would have taken me a few weeks to even understand the initial code to begin with. I haven't done C work in a long ass time and have zero knowledge of even what sub pixel sampling means.
With DS4 took me a few days and a couple of dollars. And by few days I mean I checked on it a few minutes every half hour or so a few times.
I don't understand the code it wrote but it's been in production for a while now and no issues so it's good. Ended up speeding up our video processing pipeline by 20-30%.
So while I do agree that it is cool you were able to do this, I‘ll say:
Sending in the patches but refusing to take responsibility for them is a surefire way to contribute to maintainer burnout. Please don’t do this. Either commit to fixing something and driving the PR to merge, or abstain from it entirely.
The bottleneck isn’t the speed of coding, and what you’re doing here is actively worsening the situation.
So what should newcomers do who haven't yet gained enough expertise to ask LLMs the right questions?
Newcomers have to do exactly the same what they did years and years ago. Practice the craft and gain experience by doing things.
And the craft is loose term, it can mean anything you like to get better at.
“asking the right questions” is built on years of experience doing the things now being offloaded to AI
“asking the right questions” is also a moving target with each model release
People simply underestimate the value of doing the work and think that the end result is all that matters
> “asking the right questions” is built on years of experience doing the things now being offloaded to AI
https://en.wiktionary.org/wiki/eat_one%27s_seed_corn#English
Except the steering itself is also disappearing, the same prompts from just 6 months ago now need much less steering, AIs are learning to even ask back in certain cases to persuade people with no experience towards the most likely correct choice