> If you are using LLMs to write anything more than a if(else)/for block at a time you are doing it wrong
Then what value are they actually adding?
If this is all they are capable of, surely you could just write this code yourself much faster than trying to describe what you want to the LLM in natural language?
I cannot imagine any decently competent programmer gaining productivity from these tools if this is how limited they still are
This is how I feel. I mentioned this to a couple of friends over a beer and their answer was that there are many not "decently competent programmer"s in the industry currently and they benefit immensely from this technology, at the expense of the stability and maintainability of the system they are working on.
Albeit they are fairly context aware as to what you are asking. So they can save a lot of RTFM and code/test cycles. At times they can look at the functions that are already built, and write new ones for you, if you can begin to describe the function well.
But if you want to write a good function, like written to fit tightly to specifications. Its too much English. You need to describe in steps what is to be done, plus exceptions. And at some point you are just doing logic programming(https://en.wikipedia.org/wiki/Logic_programming) In the sense that whole english text looks like a list of and/or situations + exceptions.
So you have to go one atomic step(a decision statement and a loop) at a time. But thats a big productivity boost too. Reason being able to put lots of text in place without you having to manually type it out.
>>you could just write this code yourself much faster than trying to describe what you want to the LLM in natural language?
Honestly speaking most of coding is manually laborious if you don't know touch typing. And even if you did know its a chore.
I remember when I started using co-pilot with react it was doing a lot of otherwise typing work I'd have to do.
>>I cannot imagine any decently competent programmer gaining productivity from these tools if this is how limited they still are
IMO opinion, my brain atleast over the years has seen so many code patterns, debugging situations and what to anticipate and assemble as I go, that having some intelligent typing assistant is a major productivity boost.
>>Why are people so bullish on them?
Eventually newer programming languages will come along and people will build larger things.
I'll give a serious answer. The AI code completions are way faster and way easier to read for issues than me typing code out by hand. That's already a good 10-20% productivity boost right there for me.
Which I highly doubt for anything other than greenfield project. When you look at any mature open source project, it’s mostly small commits, but a large context is required in order to make these. If you’re in boilerplate land, becoming fluent in your editor and using snippets can bring a more advantageous boost.
No I work in a huge company and many of our systems are 10+ years old. I did have a lot of snippets but AI is good at handling new things I haven't seen before and wouldn't have had a snippet for yet. It's also great for extending configurations / large switch statements / etc. the kind of stuff you see in big codebases.
It's terrible when you get to complex code, but I'd rather spend most of my time there anyways
Supercool bro'! Show these luddites! See non-believers this one works at a huge company solving hard tasks. So again please teach us! How did you get the 10-20%? How did you measure it? What methodology? Control group? Is it 10-20 more projetcs done? Or profits!!??? I bet its profits!! This guy is living the dream!!!
Honestly, a lot of the problems people have with programming that they use AI to solve can be solved with better language design and dev tools.
For example, I like LLMs because they take care of a lot of the boilerplate I have to write.
But I only have to write that boilerplate because it's part of the language design. Advances in syntax and programming systems can yield similar speedups in programming ability. I've seen a 100x boost in productivity that came down to switching to a DSL versus C++.
Maybe we need more DSLs, better programming systems, better debugging tools, and we don't really need LLMs the way LLM makers are telling us? LLMs only seem so great because our computer architecture, languages and dev tooling and hardware are stuck in the past.
Instead of being happy with the Von Neumann architecture, we should be exploring highly parallel computer architectures.
Instead of being happy with imperative languages, we should be investing heavily in studying other programming systems and new paradigms.
Instead of being happy coding in a 1D text buffer, we should be investing more in completely imaginative ways of building programs in AR, VR, 3D, 2D.
LLMs are going to play a part here, but I think really they are a band-aid to a larger problem, which is that we've climbed too high in one particular direction (von-neuman/imperative/text) and we are at a local maxima. We've been there since 2019 maybe.
There are many other promising peaks to climb, avenues of research that were discovered in the 60s/70s/80s/90s have been left to atrophy the past 30 years as the people who were investigating those paths refocused or are now gone.
I think all these billions invested in AI are going to vaporize, and maybe then investors will focus back on the fundamentals.
LLMs are like the antenna at the top of the Empire State Building. Yes, you can keep going up if you climb up there, but it's unstable and eventually there really is a hard limit.
If we want to go higher that that, we need to build a wider and deeper foundation first.
Then what value are they actually adding?
If this is all they are capable of, surely you could just write this code yourself much faster than trying to describe what you want to the LLM in natural language?
I cannot imagine any decently competent programmer gaining productivity from these tools if this is how limited they still are
Why are people so bullish on them?