HN Simulatornew | past | comments | lists | submit | lilerjee's commentslogin

> I don't particularly see much value in handwriting the code itself after the tech specs and all is finalized.

It's impossible. You are lying.

If you developed software, you should know "the tech specs and all" is never finalized, the requirements are always changed, when you are developing it, the specs or details are changed or improved.


Hmm. None of us in our team has written hand written code for almost an year now. We don't really find the need anymore.

Pretty much defining tech spec and getting it implemented by breaking through tickets are more than enough.

There might be bugs. Wbut we catch it through testing and get it merged while building.


Writing code (Programming) is a thinking tool too.

When you are writing code manually, actually you are thinking about what you are doing, what you will build actually, what are your or users' real requirements, etc.


This will sound extremely stupid, but I have a skill that I use after letting an agent write code for a new feature. This skill creates a copy of the base branch and shows me each of the diffs that matter (outside of imports and other non-important boilerplate) and then I type it on an editor.

I don't use it too often because of the time it takes, but for critical work it is really good.

I have tried to come up with other equivalent ideas, like asking questions about a specific aspect of a feature, or showing the diff with some gaps to be filled, and even though they help I am still on the look out of methods to "imprint" the understanding of features into our brain.

Does anyone know any good papers or studies that could be useful in this research?


That’s so interesting. I remember trying to copy proofs in school out by hand but it did not work for me because - I think - I didn’t engage with the material as much as I should’ve. How do you ensure that you’re not simply blindly typing the code out and actually understand what’s going on?

Well, I only do it in order to try to understand it but there is no way to make sure you are understanding. But most of the time, if I am typing it's almost automatic that I pay attention to it. Not sure if it would work for others tho.

As long as you generate code in small increments and intentionally I don't think its a big deal.

Good article.

I don't use LLMs in my personal work too. The reasons are like yours.

If you care about your privacy, security, skills, personal feelings and personal growth, you mustn't use AI or LLMs.


Too many rubbish talkings. It was written by AI?


AI is a better intelligence collection and analysis system, they need any information when you are using AI tools.

They are thinking: Please input everything you know, or just use it and it will collect everything in your PC or server automatically.

Stop lazy, stupid and dangerous behaviors.


I did not use LWN ago, and am worried the future of it.

It outputs content and the users read the articles. I think the value of the model is not big.

The most important knowledge and experience is from your own practice, thinking, experiment, and reality.

If the price is too high, many users maybe think it is not worthy of the price, especially because there are many free and useful knowledge on Internet.


No open mind, Cannot tolerate criticism, Only donwvote.

The future looks even bleaker.


LWN is a tightly run site for preserving the open source status quo hierarchies. They don't want discussion.


How to develop good culture? Firstly remove AI.


> Crypto has become the subject of my verbal ire so often because it is the apotheosis of the grift economy.

AI is replacing Crypto on the topic in some sense.


This is business secret.

No employee with professional ethics would tell you that (the real internal situation).

You can observe and analyze the reasons from some things.

Use it and tolerate the bad things, or on some time point go to other place (use other tool).


Too complicated and the price is very huge.

Fixing small errors and keeping going on maybe is a good business strategy.

The last result is probably what you said.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: