LLMs in Programming

Try using the LLM as a learning tool, rather than asking it to do your job.I don't really like the way LLMs code. I like coding. So I mostly do that myself.However I find it enormously useful to be able to ask an LLM questions. You know the sort of question you need to ask to build an intuition for something? Where it's not a clear problem answer type question you could just Google. It's the sort of thing where you'd traditionally have to go hunt down a human being and

Don't have faith in LLMs. don't trust them.treat them like a new hire - you've got to take some time to judge what their capabilities are, how they're going to fit into your workflow, and how you can make their output useful. they're going to be bad at some things, and they're going to be good at some things. and maybe they're not going to be a good fit at all. but sometimes they will be really helpful, and ignoring that and deciding to do everything you

This comment doesn't deserve the downvotes its getting, the author is right, and I'm having the same experience.LLM outputs aren't always perfect, but that doesn't stop them from being extremely helpful and massively increasing my productivity.They help me to get things done with the tech I'm familiar with much faster, get things done with tech I'm unfamiliar with that I wouldn't be able to do before, and they are extremely helpful for learning as well.<p

No matter how good or fast you are, you will never beat the LLM. What you're saying is akin to "your math is faster than a calculator" and I'm willing to bet it's not. LLMs are not perfect and will require intervention and fixing but if it can get you 90% there, that's pretty good. In the coming years, you'll soon find your peers are performing much faster than you (assuming you program for a living) and you will have no choice but you do you.

Any recent LLM can converse in more natural languages than you, can write code in more programming languages than you and do it much quicker than you, can find bugs quicker than you, can extract useful information from large amounts of text quicker than you, can produce a more balanced take on many issues than you. The list goes on. Your denial of this is either ignorance or a coping mechanism. Either way, I recommend learning more about the subject and getting meaningful experience with it in o

It depends. For a task I know well the LLM is often much worse. If I'm being asked to do something brand new, the LLM does speed me up quite a bit and let me build something I might have gotten stuck on otherwise. The problem is that although I did "build the thing," it's not clear I really gained any meaningful skills. It feels analogous to watching a documentary vs. reading a book. You learned _something_, but it's honestly pretty superficial.

I've been programming for a few decades. I love LLMs. They make tedious things quick. Help me resolve gnarly issues. Make short work of writing unit tests. Generate oodles of boilerplate at will. Etc. It makes me more productive and less reluctant to take on risky things. By risky I mean things that formerly would have likely derailed my busy schedule because I'd get side tracked for to long and would have to de-prioritize more important stuff.Anyway, resistance is futile. You will

I entirely agree about their utility.HN, and the internet in general, have become just an ocean of reactionary sandbagging and blather about how "useless" LLMs are.Meanwhile, in the real world, I've found that I haven't written a line of code in weeks. Just paragraphs of text that specify what I want and then guidance through and around pitfalls in a simple iterative loop of useful working code.It's entirely a learned skill, the models (and very importantly the

LLMs haven't made me dumber, but they have made me lazier. I think about writing code by hand now and groan.

ChatGPT with GPT4 has made me much better and faster at solving programming problems, both at work and for working on personal projects.Many people are still sleeping on how useful LLMs are. There's a lot of related things to be skeptical about (big promises, general AI, does it replace jobs, all the new startups that are basically dressed up API calls...) but if you do any kind of knowledge work, there's a good chance that you could it much better if you also used an LLM.