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

201–210 of 342 posts

Re: How I program with LLMs

#201

Post by 999900000999 »

I still find most LLMS to be extremely poor programmers .

Claude will often generate tons and tons of useless code quickly using up it's limit. I often find myself yelling at it to stop.

I was just working with it last night.

"Hi Claude, can you add tabs here.":

Claude will then start generating MainContent.

DeepSeek, despite being free does a much better job than Claude. I don't know if it's smarter, but whatever internal logic it has is much more to the point.

Claude also has a very weird bias towards a handful of UI libraries that has installed, even if those wouldn't be good for your project. I wasted hours on shancn UI which requires a very particular setup to work.

LLM's are generally great at common tasks using a top 5( popularity) language.

Ask it to do something in a Haxe UI library and it'll make up functions that *look* correct.

Overall I like them, they definitely speed things up. I don't think most experienced software engineers have much to worry about for now. But I am really worried about juniors. Why higher a junior engineer, when you can just tell your seniors they need to use Copilot to crank out more code

Re: How I program with LLMs

#202

Post by mark_l_watson »

oogali wrote: post #160
brabel wrote: post #157

Earlier quoted context omitted.

Yes. If the AI is not integrated with the IDE, it's not as helpful. If there were an IDE plugin that let you use a local model, perhaps that would be an option, but I haven't seen that (Github Copilot allows selecting different models, but I didn't check more carefully whether that also includes a local one, anyone knows?).

It’s doable as it’s what I use to experiment. Ollama + CodeGPT IntelliJ plugin. It allows you to point at a local instance.

I also use Ollama for coding. I have a 32G M2 Mac, and the models I can run are very useful for coding and debugging, as well as data munging, etc. That said, sometimes I also use Claude Sonnet 3.5 and o1. (BTW, I just published an Ollama book yesterday, so I am a little biassed towards local models.)

Re: How I program with LLMs

#203

Post by cudgy »

notjoemama wrote: post #7

Our company has a no AI use policy. The assumption is zero trust. We simply can’t know whether a model or its framework could or would send proprietary code outside the network. So it’s best to assume all LLMs/AI is or will send code or fragments of code. While I applaud the incredible work by their creators, I’m not sure how a responsible enterprise class company could rely on “trust us bro” EULAs or repo readmes.

Does your company develop software overseas where legal action is difficult? Or where their ip could be nationalized or secretly stolen? Where network communications are monitored and saved?

Re: How I program with LLMs

#204

Post by btbuildem »

The search part really resonates with me. I do a lot of odd/unusual/one-off things for my side projects, and I use LLMs extensively in helping me find a path forward. It's like an infinitely patient, all-knowing expert that pulls together info from any and all domain. Sometimes it will have answers that I am unable to find another way (eg, what's the difference between "busy s..." and "busy p..." AT command response on the esp8285?). It saves me hours of struggle, and I would not want to go back to the old ways.

Re: How I program with LLMs

#205

Post by imhoguy »

bangaladore wrote: post #19

The killer feature about LLMs with programming in my opinion is autocomplete (the simple copilot feature). I can probably be 2-3x more productive as I'm not typing (or thinking much). It does a fairly good job pulling in nearby context to help it. And that's even without a language server. Using it to generate blocks of code in a chat like manner in my opinion just never works well enough in the domains I use it on.…

Both autocomplete and chat are half-way UX solutions. Really what I need is some kind of mix of in-place chat with completion.

For context, very often I have to put some comment before the line for completion to set an expectation context.

Instead editor should allow me to influence completion with some kind of in-place suggestion input available under keyboard shortcut. Then I could type what I want into such input and when I hit Enter or Tab the completion proposal appears. Even better if it would let me undo/modify such input, and have shortcuts like "show me different option", "go back to previous".

Re: How I program with LLMs

#206

Post by cudgy »

golergka wrote: post #108
notjoemama wrote: post #7

Our company has a no AI use policy. The assumption is zero trust. We simply can’t know whether a model or its framework could or would send proprietary code outside the network. So it’s best to assume all LLMs/AI is or will send code or fragments of code. While I applaud the incredible work by their creators, I’m not sure how a responsible enterprise class company could rely on “trust us bro” EULAs or repo readmes.

What's the realistic attack scenario? Will Sam Altman steal your company's code? Or will next version of GPT learn on your secret sauce algorithms and then your competitors will get them when they generate code for their tasks and your company loses its competitive advantage? I'm actually sure that there are companies for which these scenarios are very real. But I don't think there's a lot of them. Most of the code o…

So why bother securing anything at all if not willing to secure the raisons d'être? Doesn’t that suggest that these companies are trivial entities?

Re: How I program with LLMs

#207

Post by harrall »

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…

I believe it’s more that people hate trying new tools because they’ve already made their choice and made it their identity.

However, there are also people who love everything new and jump onto the latest hype too. They try new things but then immediately advocate it without merit.

Where are the sane people in the middle?

Re: How I program with LLMs

#208

Post by big_youth »

ignoramous wrote: post #123
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…

> [David, Former staff engineer at Google ... CTO of Tailscale,] 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... Don't doubt for a second the pedigree of founding engs at Tailscale, but David is careful to point out exactly why LLMs work for them (but might not for others): I am doing a particular kind of…

> If you spend more time proving your optimization of a cryptographic algorithm is not vulnerable to timing attacks than you do writing the code, I don't think any of my observations here are going to be useful to you.

I am not a software dev I am a security researcher. LLM's are great for my security research! It is so much easier and faster to iterate on code like fuzzers to do security testing. Writing code to do a padding oracle attack would have taken me a week+ in the past. Now I can work with an LLM to write code and learn and break within the day.

It has accelerated my security research 10 fold, just because I am able to write code and parse and interpret logs at a level above what I was able to a few years ago.

Re: How I program with LLMs

#209

Post by SkyBelow »

mlepath wrote: post #2

The first rule of programming with LLMs is don't use them for anything you don't know how to do. If you can look at the solution and immediately know what's wrong with it, they are a time saver otherwise... I find chat for search is really helpful (as the article states)

How you use the LLM matters.

Having an LLM do something for you that you don't know how to do is asking for trouble. An expert likely can off load a few things they aren't all that important, but any junior is going to dig themselves into a significant hole with this technique.

But asking an LLM to help you learn how to do something is often an option. Can't one just learn it using other resources? Of course. LLMs shouldn't be a must have. If at any point you have to depend upon the LLM, that is a red flag. It should be a possible tool, used when it saves time, but swapped for other options when they make sense.

For an example, I had a library I was new to and asked copilot how to do some specific task. It gave me the options. I used this output to go to google and find the matching documentation and gave it a read. I then when back to copilot and wrote up my understanding of what the documentation said and checked to see if copilot had anything to add.

Could I have just read the entire documentation? That is an option, but one that costs more time to give deeper expertise. Sometimes that is the option to go with, but in this case having a more shallow knowledge to get a proof of concept thrown together fit my situation better.

Anyone just copying an AI's output and putting it in a PR without understanding what it does? That's asking for trouble and it will come back to bite them.

Re: How I program with LLMs

#210

Post by bpizzi »

brabel wrote: post #157
EagnaIonat wrote: post #104

Earlier quoted context omitted.

Have you tried using Ollama? You can download and run an LLM locally on your machine. You can also pick the right model for the right need and it's free.

Yes. If the AI is not integrated with the IDE, it's not as helpful. If there were an IDE plugin that let you use a local model, perhaps that would be an option, but I haven't seen that (Github Copilot allows selecting different models, but I didn't check more carefully whether that also includes a local one, anyone knows?).

> (Github Copilot allows selecting different models, but I didn't check more carefully whether that also includes a local one, anyone knows?).

To my knowledge, it doesn't.

On Emacs there's gptel which integrates quiet nicely different LLM inside Emacs, including a local Ollama.

> gptel is a simple Large Language Model chat client for Emacs, with support for multiple models and backends. It works in the spirit of Emacs, available at any time and uniformly in any buffer.

https://github.com/karthink/gptel

Post reply on HN