Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How I program with LLMs

crawshaw.io

Post reply on HN
Print view View original

171–180 of 342 posts

Re: How I program with LLMs

#171

Post by psychoslave »

bsenftner wrote: post #143
antirez wrote: post #120

Earlier quoted context omitted.

I have also many years of programming experience and find myself strongly "accelerated" by LLMs when writing code. But, if you think at it, it makes sense that many seasoned programmers are using LLMs better. LLMs are a helpful tool, but also a hard-to-use tool, and in general it's fair to think that better programmers can do a better use of some assistant (human or otherwise): better understanding its strengths, ide…

Communication skills are the keys to using LLMs. Think about it: every type of information you want is in them, in fact it is there multiple times, with multiple levels of seriousness in the treatment of the idea. If one is casual in their request, using casual language, then the LLM will reply with a casual reply because that matched your request best. To get a hard, factual answer from those that are experts in a s…

>every type of information you want is in them

Actually, I'm afraid that no. It won't give us the step by step scalable processes to make humanity as a whole enter in a loop of indefinitely long period of world peace, with each of us enjoying life in its own thriving manner. That would be great information to broadcast, though.

Also it equally has ability to produce large pile of completely delusional answers, that mimics just as well genuinely sincere statements. Of course, we can also receive that kind of misguiding answers from humans. But the amount of output that mere humans can throw out in such a form is far more limited.

All that said, it's great to be able to experiment with it, and there are a lot of nice and fun things to do with it. It can be a great additional tool, but it won't be a self-sufficient panacea of information source.

Re: How I program with LLMs

#172

Post by simondotau »

midasz wrote: post #122
simondotau wrote: post #76

I've recently started using Cursor because it means I can now write python where two weeks ago I couldn't write python. It wrote the first pass of an API implementation by feeding it the PDF documentation. I've spent a few days testing and massaging it into a well formed, well structured library, pair-programming style. Then I needed to write a simple command line utility, so I wrote it in Go, even though I've never…

But you're not really writing python right? You're instructing a tool to generate python. Kinda like saying I'm writing bytecode while I'm actually just typing Java.

I am really writing python. The LLM is a substitute for having foreknowledge of this particular language's syntax and grammar, but I'm still debugging like a "real" programmer and I'm still editing/refining the code like a "real" programmer, because I am.

Probably half the lines of code were written by me, because I do know how to write code.

Here's what I wrote if you're curious: https://github.com/sjwright/zencontrol-python/

Re: How I program with LLMs

#173

Post by bsenftner »

psychoslave wrote: post #171
bsenftner wrote: post #143

Earlier quoted context omitted.

Communication skills are the keys to using LLMs. Think about it: every type of information you want is in them, in fact it is there multiple times, with multiple levels of seriousness in the treatment of the idea. If one is casual in their request, using casual language, then the LLM will reply with a casual reply because that matched your request best. To get a hard, factual answer from those that are experts in a s…

>every type of information you want is in them Actually, I'm afraid that no. It won't give us the step by step scalable processes to make humanity as a whole enter in a loop of indefinitely long period of world peace, with each of us enjoying life in its own thriving manner. That would be great information to broadcast, though. Also it equally has ability to produce large pile of completely delusional answers, that m…

> It won't give us the step by step scalable processes to make humanity as a whole enter in a loop of indefinitely long period of world peace

That's not anywhere, that's a totally unsolved and open ended problem, why would you think an LLM would have that?

Re: How I program with LLMs

#174

Post by lm28469 »

aulin wrote: post #170
lm28469 wrote: post #167

Earlier quoted context omitted.

> I’m not sure how a responsible enterprise class company could rely on “trust us bro” EULAs or repo readmes. Isn't that what we do with operating systems, internet providers, &c. ?

How is that related? we're talking of continuously sending proprietary code and related IP to a third party, seems a pretty valid concern to me. I, for one, work every day with plenty of proprietary vendor code under very restrictive NDAs. I don't think they would be very happy knowing I let AIs crawl our whole code base and send it to remote language models just to have fancy autocompletion.

Do you read every single line of code of every single dependency you have ? I don't see how llms are more of a threat than a random compromised npm package or something from a OS package manager. Chances are you're already relying on tons and tons of "trust me bro" and "it's opensource bro don't worry, just read the code if you feel like it"

Re: How I program with LLMs

#175

Post by fmbb »

bsenftner wrote: post #173
psychoslave wrote: post #171

Earlier quoted context omitted.

>every type of information you want is in them Actually, I'm afraid that no. It won't give us the step by step scalable processes to make humanity as a whole enter in a loop of indefinitely long period of world peace, with each of us enjoying life in its own thriving manner. That would be great information to broadcast, though. Also it equally has ability to produce large pile of completely delusional answers, that m…

> It won't give us the step by step scalable processes to make humanity as a whole enter in a loop of indefinitely long period of world peace That's not anywhere, that's a totally unsolved and open ended problem, why would you think an LLM would have that?

If what you meant was

> Think about it: every type of already solved problem you want information about is in them, in fact it is there multiple times, with multiple levels of seriousness in the treatment of the idea.

then that was not clear from your comment saying LLMs contain any information you want.

One has to be careful communicating about LLms because the world is full of people that actually believe LLMs are generally intelligent super beings.

Re: How I program with LLMs

#176

Post by apwell23 »

dewitt wrote: post #52

One interesting bit of context is that the author of this post is a legit world-class software engineer already (though probably too modest to admit it). Former staff engineer at Google and co-founder / CTO of Tailscale. He doesn't need LLMs. That he says LLMs make him more productive at all as a hands-on developer, especially around first drafts on a new idea, means a lot to me personally. His post reminds me of an…

he is using llm for coding. you don't become staff engineer by being a badass coder. Not sure how they are related.

Re: How I program with LLMs

#177

Post by denvermullets »

this is almost exactly how ive been using llms. i dont like the code complete in the ide, personally, and prefer all llm usage to be narrow specific blocks of code. it helps as i bounce between a lot of side projects, projects at work, and freelance projects. not to mention with context switching it really helps keep things moving, imo

Re: How I program with LLMs

#178

Post by jprete »

gopalv wrote: post #88
dewitt wrote: post #52

One interesting bit of context is that the author of this post is a legit world-class software engineer already (though probably too modest to admit it). Former staff engineer at Google and co-founder / CTO of Tailscale. He doesn't need LLMs. That he says LLMs make him more productive at all as a hands-on developer, especially around first drafts on a new idea, means a lot to me personally. His post reminds me of an…

> That he says LLMs make him more productive at all as a hands-on developer, especially around first drafts on a new idea, means a lot to me personally. There is likely to be a great rift in how very talented people look at sharper tools. I've seen the same division pop up with CNC machines, 3d printers, IDEs and now LLMs. If you are good at doing something, you might find the new tool's output to be sub-par over wha…

This is a good characterization. I'm precision-driven and know what I need to do at any low level. It's the high-level definition that is uncertain. So it doesn't really help to produce a dozen prototypes of an idea and pick one, nor does it help to fill in function definitions.

Re: How I program with LLMs

#179

Post by tikkun »

gopalv wrote: post #88
dewitt wrote: post #52

One interesting bit of context is that the author of this post is a legit world-class software engineer already (though probably too modest to admit it). Former staff engineer at Google and co-founder / CTO of Tailscale. He doesn't need LLMs. That he says LLMs make him more productive at all as a hands-on developer, especially around first drafts on a new idea, means a lot to me personally. His post reminds me of an…

> That he says LLMs make him more productive at all as a hands-on developer, especially around first drafts on a new idea, means a lot to me personally. There is likely to be a great rift in how very talented people look at sharper tools. I've seen the same division pop up with CNC machines, 3d printers, IDEs and now LLMs. If you are good at doing something, you might find the new tool's output to be sub-par over wha…

Intersting.

So engineers that like to iterate and explore are more likely to like LLMs.

Whereas engineers that like have a more rigid specific process are more likely to dislike LLMs.

Re: How I program with LLMs

#180

Post by owebmaster »

I thought his project, sketch.dev is of very poor quality. I wouldn't ship something like this - the auth process is awful and broke, I still can't login. If after 14 hours of the post the service is still rugged to death, it also means the scalability of the app is bad. If we are going to use LLMs to replace hours of programming, we should aim for quality too.
Post reply on HN