Hacker News Reader

Comment by kamaludu | Hacker News Reader

Yes, the code is big and bulky, i know. But i am a single person, not a team. I write simple and clear for me, because i need to mantain it. Only Bash, zero dependencies, i like this.

thank you for your comment!

View on HN

> I write

You mean the LLM writes the code based on your instructions (that's fine, I guess, but 5KLOC is huge for this kind of script).

Architecture and structure are my decisions, LLM are instruments, simple executors, today i think are commonly used. Write code with LLM is not "push a button", it's a technical way of work, needs study and practice. 5k lines are months of work, debug, refactor, testing. 5k lines are the result of a long (and difficult) work, but LLM helps your productivity. The most important thing, for the humans, are the architectural decisions, and understanding how your current LLM reasoning and behavior. I decide architecture and structure; LLM only writes code (that need debug and testing), LLM are executors, not automatic. LLM are only software, and are new instruments to learn. Important thing: I use only free plan, of LLMs that have a real free plan.

I think the fact that you only use the free plan might correlate with the code size and the need to debug/test a lot.

I don't think , I can pay if it's really good for this work, but I've seen the characteristics of pay plan and are not really better for my use case. The free plan is not the reason for the code size; the architecture is the reason. the best choice for me, for this work, is to have a real AI (not a toy installed on a laptop) without limitations and filters, but for this need many tens of thousands of €

Why are you posting this if you know it is of poor quality then?

It's certainly not because you are proud of yourself, it has been generated.

So I genuinely wonder why?

I don't think it is of poor quality. I post this because I wish it is good for others. It's not auto generated, I made this.

Perhaps not, but if an LLM is being used it is better to be honest than not, in my opinion.

It's not out of attempting to make your work look any worse than it is, but a fundamental respect for the audience that read your code. I understand the power of LLMs, hell I'm using one to write some of my own software and diligently reading the code it generates and designing the architecture around it myself, but I would always try and be honest about what went into the code that I'm showing someone.

For ethical principles I 100% agree with you. I used LLMs to generate parts of the code, but the architecture, integration, debugging and testing are mine. It took me months in my free time. So, what can I say to be 100% honest?

It's likely if you lead with this and acknowledged that there will be issues of the sort identified in the thread within your code the feedback you've got wouldn't be as harsh.

You're right, starting with that context would have helped. It's an experimental project and of course there will be imperfections, whether written by me or with LLM assistance. I did my best.

Reply on news.ycombinator.com