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

Using AI for Coding: My Journey with Cline and LLMs

pgaleone.eu

Post reply on HN
Print view View original

11–20 of 97 posts

Re: Using AI for Coding: My Journey with Cline and LLMs

#11

Post by rfw300 »

WD-42 wrote: post #6
doug_durham wrote: post #3

Earlier quoted context omitted.

Because as op pointed out it's faster. It has ready access to the correct usage of different libraries.

So does the language features of basically any modern editor.

Not really - there's a difference between having the docstring of a function available for you to read, and a model which has learned from thousands of examples how to use a particular API and integrate it into a larger set of instructions. The latter is vastly faster and takes much less human work than the former.

Re: Using AI for Coding: My Journey with Cline and LLMs

#12

Post by girvo »

rfw300 wrote: post #11
WD-42 wrote: post #6

Earlier quoted context omitted.

So does the language features of basically any modern editor.

Not really - there's a difference between having the docstring of a function available for you to read, and a model which has learned from thousands of examples how to use a particular API and integrate it into a larger set of instructions. The latter is vastly faster and takes much less human work than the former.

Except when it consistently gets said particular API wrong. I was using it to do basic graphql-yoga setup with R1 and then Claude Sonnet 3.5 and they both output incorrect usage, and got stuck in a loop trying to fix it.

If it can’t do something that basic and that common using a language and toolset with that much training data, then I’m pessimistic personally.

I’m yet to see Copilot be useful for any of my juniors when we pair, it gets in the way far more than it helps and it is ruining their deeper understanding, it seems.

I’ll continue trying to use these tools, but I swear you’re overselling their abilities even still.

Re: Using AI for Coding: My Journey with Cline and LLMs

#13

Post by mkw5053 »

cyanydeez wrote: post #4

Anyone got a line on a local first AI Tooling. Happy to pay100$. Don't want a subscription.

You could try OpenHands + OpenRouter + Llama (https://docs.all-hands.dev/modules/usage/llms/openrouter) I haven't tried it and don't know how it would go.

Re: Using AI for Coding: My Journey with Cline and LLMs

#14

Post by simonw »

ivoras wrote: post #2

I did a similar thing but with backend-heavy code, and I agree with this assessment: > In particular, I asked ChatGPT to write a function by knowing precisely how I would have implemented it. This is crucial since without knowing the expected result and what every line does, I might end up with a wrong implementation. In my eyes, it makes the whole idea of AI coding moot. If I need to explain every step in detail - a…

LLMs are way, way faster at typing code than I am. I often dictate to them exactly what I need and it saves me a bunch of time.

Re: Using AI for Coding: My Journey with Cline and LLMs

#15

Post by simonw »

girvo wrote: post #12
rfw300 wrote: post #11

Earlier quoted context omitted.

Not really - there's a difference between having the docstring of a function available for you to read, and a model which has learned from thousands of examples how to use a particular API and integrate it into a larger set of instructions. The latter is vastly faster and takes much less human work than the former.

Except when it consistently gets said particular API wrong. I was using it to do basic graphql-yoga setup with R1 and then Claude Sonnet 3.5 and they both output incorrect usage, and got stuck in a loop trying to fix it. If it can’t do something that basic and that common using a language and toolset with that much training data, then I’m pessimistic personally. I’m yet to see Copilot be useful for any of my juniors…

The way to fix that is to find an example of correct usage of that API and paste that example in at the start of the prompt.

This technique can reliably make any good LLM fluent in an API that it's never seen in its training data.

Re: Using AI for Coding: My Journey with Cline and LLMs

#16

Post by bcrosby95 »

simonw wrote: post #14
ivoras wrote: post #2

I did a similar thing but with backend-heavy code, and I agree with this assessment: > In particular, I asked ChatGPT to write a function by knowing precisely how I would have implemented it. This is crucial since without knowing the expected result and what every line does, I might end up with a wrong implementation. In my eyes, it makes the whole idea of AI coding moot. If I need to explain every step in detail - a…

LLMs are way, way faster at typing code than I am. I often dictate to them exactly what I need and it saves me a bunch of time.

So you would say typing speed matters?

Re: Using AI for Coding: My Journey with Cline and LLMs

#17

Post by tomrod »

mkw5053 wrote: post #13
cyanydeez wrote: post #4

Anyone got a line on a local first AI Tooling. Happy to pay100$. Don't want a subscription.

You could try OpenHands + OpenRouter + Llama ( https://docs.all-hands.dev/modules/usage/llms/openrouter ) I haven't tried it and don't know how it would go.

Llama.vscode and llama.vim look promising.

Re: Using AI for Coding: My Journey with Cline and LLMs

#18

Post by throwup238 »

simonw wrote: post #15
girvo wrote: post #12

Earlier quoted context omitted.

Except when it consistently gets said particular API wrong. I was using it to do basic graphql-yoga setup with R1 and then Claude Sonnet 3.5 and they both output incorrect usage, and got stuck in a loop trying to fix it. If it can’t do something that basic and that common using a language and toolset with that much training data, then I’m pessimistic personally. I’m yet to see Copilot be useful for any of my juniors…

The way to fix that is to find an example of correct usage of that API and paste that example in at the start of the prompt. This technique can reliably make any good LLM fluent in an API that it's never seen in its training data.

At this point with Cursor you can have it index the online docs by giving it a base URL and have it automatically RAG the relevant content into the chat (using the @ symbol to reference the docs). Both Windsurf and Cursor also support reading from URLs (iirc Aider does too).

I’ve had better luck with manually including the page but including the indexed docs is usually enough to fix API mistakes.

Re: Using AI for Coding: My Journey with Cline and LLMs

#19

Post by therealpygon »

girvo wrote: post #12
rfw300 wrote: post #11

Earlier quoted context omitted.

Not really - there's a difference between having the docstring of a function available for you to read, and a model which has learned from thousands of examples how to use a particular API and integrate it into a larger set of instructions. The latter is vastly faster and takes much less human work than the former.

Except when it consistently gets said particular API wrong. I was using it to do basic graphql-yoga setup with R1 and then Claude Sonnet 3.5 and they both output incorrect usage, and got stuck in a loop trying to fix it. If it can’t do something that basic and that common using a language and toolset with that much training data, then I’m pessimistic personally. I’m yet to see Copilot be useful for any of my juniors…

That is far more likely to happen when it is relying on compressed knowledge of documentation and usage for an API it would have seen (comparatively) only a few times in training. That is where the various types of memory, tool calling and supplementary materials being fed in can make them significantly more situationally useful.

The LLMs you mention are first and foremost a “general knowledge” machine rather than a domain expert. In my opinion, Junior developers are the least likely to benefit from their use because they have neither the foundational understanding to know when the approach is wrong, nor the practical experience to correct any mistakes. An LLM can replace a junior dev because we expect the mistakes and potentially poor quality, but you don’t really want a junior developer doing code reviews for another junior developer before pushing code.

Re: Using AI for Coding: My Journey with Cline and LLMs

#20

Post by guelo »

ivoras wrote: post #2

I did a similar thing but with backend-heavy code, and I agree with this assessment: > In particular, I asked ChatGPT to write a function by knowing precisely how I would have implemented it. This is crucial since without knowing the expected result and what every line does, I might end up with a wrong implementation. In my eyes, it makes the whole idea of AI coding moot. If I need to explain every step in detail - a…

It’s a better, faster, personalized Stack Overflow. Just like SO you might be led down the wrong path by an answer, but if you’re a programmer and you say you don’t get value out of Stack Overflow I don’t believe you.
Post reply on HN