Hacker News Reader

Comment by javaunsafe2019 | Hacker News Reader

javaunsafe2019

I don’t know how people can claim such huge success using copilot and such. I also own a subscription and tried to use it for coding but all task from spring boot authentication configuration to aws policies and lambdas it failed horribly.

Writing the code myself using proper documentation was the only option.

I wonder if false information is written here in the comments section for certain reasons …

View on HN

You need to spend time learning how to use it. This is difficult because there's no manual, and there's a widespread implication that it should just magically work well without you having to invest any effort in it.

If you can figure out HOW to invest that effort it becomes really valuable.

I wish I had good resources I could link you to here but I don't, which is a big part of the problem here.

You sound like you’ve had success using this tech for work. Can you tell more about your personal experience, please? I’ve tried ChatGPT a few times a year ago or so, but it was extremely frustrating, and I gave up.

Here's my "How I use LLMs and ChatGPT" series: https://simonwillison.net/series/using-llms/

Also relevant is my ai-assisted-programming tag: https://simonwillison.net/tags/ai-assisted-programming/

These examples are not much different than tutorial regurgitation imo. I would not pass this off as solving the problems that programmers have in practice, imo.

It is great for cheating at school, at least.

And maybe boilerplate.

That's one of business goals of OpenAI, which is to disrupt work and school.

Did you dismiss two years of my accumulated writing about LLMs as "tutorial regurgitation"?

Maybe you clicked the link to my series of posts that are in chronological order - https://simonwillison.net/series/using-llms/ - looked at the very first one about trying out GPT-3 from June 2022 and stopped reading.

I probably shouldn't share that link any more!

I'm a big fan of your blog simonw, and it's interesting to see how a few of the people you've responded to here aren't receptive at all to your responses.

I have become somewhat convinced that the 'ai doesn't help with programming crowd' is a little bit obtuse / entirely unwilling to experiment with new tools. It seems too much of a coincidence to see the same crowd that you've responded to struggle to perform basic website navigation and take anything away from your blog posts.

I keep experimenting because of comments like this and they still always have the same problems:

- Inability to stay self-consistent

- Random extra unused and unreachable code

- Constant wack a mole with issues they have

- Random opposite or adjacent thinking

- Assuming that how things work in one library or language must work the same in another

I then had someone say well... Just break up the work, but, that's also not what people say works for them, and also, you still have to side-eye the smaller stuff and it just gets exhausting.

A ton of studies show that if you know less than 80 about a field it'll get you to that 80 percent. And if you know more than that it'll bring you back down to 80% due to randomness, lack of data in the training, incompleteness in the model that your incomplete prompt amplifies, and just automation bias errors where you trusted something it did that you shouldn't have.

I would say that anyone claiming these things do everything are just simply new to systems.

[flagged]

Sorry, it’s a bit hard to understand from your blog. I’m a bit dyslexic, so there’s a chance I’ve mussed something obvious, but I couldn’t find any examples beyond ‘explain this short snippet’. Also, are your posts AI assisted? I find it hard to read.

I’ve tried asking ChatGPT questions about how a large codebase works, what entities should I use to implement some feature, etc. After a couple hours I realised the chat was hallucinating like crazy and turned into a yes-man, confirming all questions that assumed a yes-no answer.

The problem with your example of applying analyzing something as complex and esoteric as a codebase is that LLMs cannot reason they simply return a response based on statistical inference, so unless you followed a standard like PSR for PHP and implemented it to a 't' it simply doesn't have to context to do what you're asking it to do. If you want an LLM to be an effective programmer for a specific application you'd probably need to fine tune and provide it instructions on your coding standards.

Basically, how I've become successful using LLMs is that I solve the problem at a 9,000ft view, instruct the LLM to play different personas, have the personas validate my solution, and then instruct the LLM step-by-step to do all of the monkey work. Which doesn't necessarily always save me time upfront but in the long run it does because it makes fewer mistakes implementing my thought experiment.

Fair enough, I might be asking too much indeed, and may not be able to come up with an idea how LLMs can help me. For me, writing code is easy as soon as I understand the problem, and I sometimes spend a lot of time trying to figure out a solution that fits well within the context, so I thought I could ask an LLM what different things do and mean to help me understanding the problem surface better. Again, I may not understand something, but, at this point, I don’t understand what’s the value of code generation after I know how to solve a problem.

Do you happen to have a blog post or something showing a concrete problem that LLM helped you to solve?

In both cases there I linked to index pages that reference several years of accumulated content. None of that content is written by AI (with the exception of an occasional sentence completed by GitHub Copilot while I was typing).

I suggest reading this article for a recent example of how I use LLMs for code: https://simonwillison.net/2024/Oct/18/openai-audio/

Solve the problem at a high-level in your head, ask the LLM if your concept is correct, and then instruct the LLM to build the solution step-by-step.

It's a completely new skill that you need to learn. My productivity gains are substantial but it comes from experience building multiple applications using LLMs. I feel I learn something new every day and the tooling just gets better and better.

> I wonder if false information is written here in the comments section for certain reasons …

I find it perplexing that you resort to this instead of other plausible explanations.

I see a decent productivity boost in my personal projects which extend common technologies to solve more "boring" problems, but struggle to find much gain at work where we're deep in esoteric technologies that LLMs have little to no knowledge of.

Are you also finding gains in the latter cases?

What I've found is that the capabilities of LLMs depend on the problem solving skills of the person writing the prompts. If you know exactly what needs to be done and can translate that into step-by-step prompts it can do pretty much anything, but if you're looking for it actually solve 100% of the problem you're going to run into issues. Which is to say you still need to find the solution but you just have the LLM do the monkey work.

Maybe you should set the right expectations to find the right use.

There's plenty of copilot and cursor users out there, and developers are really not the kind of crowd that likes to pay for development tools.

Unfortunately I think it really depends what people are doing. Some people have an utterly trivial problem domain and their job is to translate fairly low level demands into code. We used to call these code monkeys. The term has fallen out of favour but they still exist. Others have a very difficult problem domain, very high level, complex problems, and spend most of their time reasoning with how to manage that inherent complexity in a functioning software system. In these discussions it's impossible to tell who is who.

Reply on news.ycombinator.com