Are people seriously getting use out of LLMs? Everything they produce is extermely sloppy in my experience, like actually mostly useless. I really dont understand the hype. Its very confusing.
So I walk, program, sit, get coffee, read a bit, come back and review the code. Most of the time it's fine, sometimes I had forgotten to mention something, and have to correct it, but this step doesn't take more than ~15 mins.
I then have a feature that would've taken me multiple days. Not because I need multiple days, but because I do not have the 8 hours of continuous time to work on it.
People have forgotten that when you start your programming day, you have to get up to speed which takes me longer than others. Let's say this takes ~15 mins. That means that if you spend 2 hours programming, ~12% of that was just getting back into the groove. LLMs do this instantly, it reads context, you can ask it questions, and you're up to speed again in less than a minute.
The point here is not that LLMs provide high quality code, but they do save you a bit of time and energy, which is worth a lot in my opinion.
A lot of inventions haven't been that ground-breaking; only there to save time. You can wash the dishes by hand, but you can also have a machine do it while you go watch TV.
I feel like everything I apply these things to sends me up a much messier and long winded route to a useable result, when compared to just doing it myself from the jump. Even the things they're ostensibly good at like sorting data comes out so messy it's practically net zero by the time you're done with quality control.
LE. I see current versions of LLM like an intern that helps me doing work. We work together, I give directions and supervision and I am responsible for the results. I cannot give complex tasks and I cannot skip checking everything, but it usually helps.
That is a wrong assumption, however. An agent is an entirely new tool in your toolbox, with no similarity to any of those you already have. You will need to learn how to wield it, like a new programming language or technology you’re unfamiliar with. You will need to do some small side projects to learn. You will need to develop a feeling for how it reacts to your inputs, when to reset the session, pass it links to documentation, or interrupt it.
None of this comes intuitively. It takes time and effort, and if you’re not ready to consciously invest that, coding agents are not going to work efficiently for you. That doesn’t take away from their utility though.
A new tool can be ultimately understood, and has a well-defined behaviour you can rely on. Then you can indeed become an expert in using a new tool.
But AI agent is more a new being (or person). It's not possible to understand them, as they are not meant to. Each of them has individuality, and can change tomorrow. There is no guarantee of a common behaviour.
So you could replace "tool" in your comment with "person" and you will see the flaw of your argument. No matter how many people you saw before, it's difficult to generalize the skillset (at least for humans there are some biological and cultural arguments why they can be generalized over). You can always meet someone different, who's, for whatever reason, not being helpful to you.
Regardless, it sure seems like developers experienced with using coding agents achieve better results than those without, which pretty much refuses your entire point.
I am not anthroporphizing them. I am just saying people are a better analogy.
> seems like developers experienced with using coding agents achieve better results than those without
That doesn't mean there is a skill involved. The same goes with people - you might just be naturally charismatic and get stuff done better with people. Doesn't mean it's a learnable skill that applies to everyone and every use case.
If you are indeed interested, this is a good beginner: https://simonwillison.net/guides/agentic-engineering-pattern...
As evidence that it is a skill beyond copy paste, you should look around (online and offline) at the really smart people who are able to derive so much from it.
The difference working with agents, is that a solo dev suddenly becomes a dev manager, who has to deal with a unreliable team of developers far out on the spectrum.
I hate the "You're holding it wrong" argument.. Because Ive held it every which way possible and its not very impressive.
But yes, many developers I know haven't coded manually in months and that includes me. That doesn't mean I drink coffee and take walks while the agent codes however. I'm now in the driving seat instead of wrangling syntax and waiting for my hands to type something.
I manage the rules, the intent, the structure. If I don't like what it does, I update the coding standard, the docs, the specs, you name it. If I want a different architecture I can actually get it done in 10min instead of a week - if at all. It's more effort than coding for me, because coding is slow and methodical and incentivizes pedantry, but for me it's a massive improvement. I have been bored out of my mind for a decade now, but I'm relatively good at what I do so I just stuck with it. I'm one of those "middle management types stuck in developer role"-type of guys so I guess my personality and proclivities have something to do with it. I also know quite a few grumpy old-school types that don't get anything done with LLMs. They can't communicate, they don't understand psychology, they don't understand architecture and have a debilitating case of missing the forest for the trees. The spread, in my experience, is massive.
Otherwise have a look here:
it can be useful for some automation... but its also dangerously dumb for that.