Live data from Hacker News

I won't deliberately use AI for programming

mahdikarimi.com

31–40 of 67 posts

Re: I won't deliberately use AI for programming

#31
post #3

I strongly disagree with this perspective. I have found GPT4 in particular to be very helpful in learning new programming languages and improving my overall coding. I still solve problems myself and I still read books, but GPT4 is the TA that I can have a conversation with about a piece of code. It's all about how you use it. If you just ask it to tell you complete answers or generate code on a blank page then you're…

Yeah this logic would have us writing everything in assembly and only using textbooks.

I believe there's a inherent benefit in learning assembly and using textbooks because it helps you better understand the software you are writing with any other language. learning hard things the hard way is good.

Re: I won't deliberately use AI for programming

#32
post #3

I strongly disagree with this perspective. I have found GPT4 in particular to be very helpful in learning new programming languages and improving my overall coding. I still solve problems myself and I still read books, but GPT4 is the TA that I can have a conversation with about a piece of code. It's all about how you use it. If you just ask it to tell you complete answers or generate code on a blank page then you're…

It's a really bad TA that has no self awareness of its limitations. You are well aware that it hallucinates, right? You probably have observed it yourself in domains you're familiar with. But how would you recognise a hallucination in something that you have no familiarity with? "Learning something new" from LLMs is like trying to learn something new from a con artist. Sure, they might actually tell you the truth, bu…

My experience has been that the hallucinations in GPT4 are actually pretty rare. But in any case, if I choose to use code it suggests I ask it for explanations and then I verify those myself by other means, e.g. tests. I think it's too strong to call it a really bad TA. I'd say it's an imperfect TA and you need to check it's work, but it's work still has great value.

Re: I won't deliberately use AI for programming

#33
As anything in life, this isn't a binary choice.

You can use an llm, while learning yourself.

I agree with the take on copilot being a hindrance on using your brain. While learning a new language it was really hard to understand whatever is being put in front of me (as autocomplete) is truly best practice or something tied together very loosely.

The extra time it takes you to google, and learn about strategies on how to code, and patterns, and design. This is what is actually valuable, being able to speak to these things in conversation when defending the code you wrote on a PR etc, it makes a difference.

Re: I won't deliberately use AI for programming

#34
I think that for some types of programmers, AI-assisted programming feels no different from what they already do.

Those types feel that the end goal of 'working code' is all that matters. Their definition of 'working' meaning that the functional requirements of the feature are met.

That mindset is an extreme. A developer's job is to solve a problem for someone, not to code, but copy/pasting code without understanding as a consistent behavior is a recipe for eventual collapse of a codebase.

I see Copilot and other LLM code generation as methamphetamine for that sort of programmer. They will feel great, but the situation around them will degrade, those surrounding them will be unhappy, and eventually it will be clear the behavior was unsustainable.

From a different angle, I would feel uneasy giving others access to my proprietary data (code), and also accepting LLM generated code into my companies products. The legal rules don't seem fully sorted.

Re: I won't deliberately use AI for programming

#35

Earlier quoted context omitted.

Yeah this logic would have us writing everything in assembly and only using textbooks.

I believe there's a inherent benefit in learning assembly and using textbooks because it helps you better understand the software you are writing with any other language. learning hard things the hard way is good.

Oh for sure! But you wouldn't argue to do this exclusively though

Re: I won't deliberately use AI for programming

#36
post #9

I have gone past the point of giving a shit. Unless it's something I really care about the minuscule details for I'll get ChatGPT to write the main chunk of code and then fix the bugs. It's no different than having a junior dev working for you, except it's quicker and doesn't piss off to lunch or go sick when you need them.

> It's no different than having a junior dev working for you In my experience it's completely different. A junior dev who wants to produce a PDF automatically will have to spend a few hours evaluating all the library options and learning their usage. But the code will certainly be free of syntax errors and will produce not-obviously-wrong output before they send it for code review. ChatGPT will select a library and k…

GPT4 is like 100:1 hits to misses for me.

Recently I switched to a different case for my home NAS. The drive caddies had a tiny cutout for a label, like 0.75 inch x 1.5 inch.

I decided to see if Chat GPT could take care of it. I asked for it to write LaTeX that would produce rectangles of that size with a light gray border, with the serial number of each drive in the rectangle.

On the first pass it got it basically right. Rectangles all the right size, right border, and all the right serial numbers.

The rectangles were all touching each other so I asked it to put a half inch between each and it did that. Then I decided I wanted fixed width font, and it accommodated that as well.

Then just for fun I asked it to draw a dinosaur using LaTeX. It advised me that this isn’t a good use of LaTeX and then used shape primitives to draw a plausible looking dinosaur.

Re: I won't deliberately use AI for programming

#37
post #3

I strongly disagree with this perspective. I have found GPT4 in particular to be very helpful in learning new programming languages and improving my overall coding. I still solve problems myself and I still read books, but GPT4 is the TA that I can have a conversation with about a piece of code. It's all about how you use it. If you just ask it to tell you complete answers or generate code on a blank page then you're…

To me GPT-4 has been very valuable when I already know the gist of what I need done, as in: I've done it before, I know the techniques and the right keywords I need, I know the tools I'll use, etc. but can't remember exactly the right incantation and would need to go read references, search Google, and so on.

Instead I pop by ChatGPT and ask it what I need done, the tools I'm using and let it write me an answer that I double-check to see if it matches what I'm looking for. It's definitely saved me a lot of time, I still go read the documentation but I have a much narrower point to start from.

I would never just copy-paste whatever it spits out, I don't trust it to generate code nor will I ever trust it to be fed with intellectual property in the prompt (mine or my employer's) but as a general assist for techniques and tools that I've been familiar with, and which could require some researching I do think it has pretty good value.

Re: I won't deliberately use AI for programming

#38

I do so many things manually that have been successfully automated for a long time. Washing dishes, splitting firewood, grinding coffee, owning manual transmission cars, I could go on. Some things are subjectively better like splitting firewood; It's more work but quieter. Some things are objectively better; washing dished by hand are cleaner. I don't think about it too much. I guess I'll just add programming to that…

I gotta side with the dishwasher. Mine heats the dishes so hot my hands would burn off doing it, and it uses 5 gallons of water for a full load.

Dont forget the chemicals that would also hurt your hands.

Re: I won't deliberately use AI for programming

#39

Earlier quoted context omitted.

It's a really bad TA that has no self awareness of its limitations. You are well aware that it hallucinates, right? You probably have observed it yourself in domains you're familiar with. But how would you recognise a hallucination in something that you have no familiarity with? "Learning something new" from LLMs is like trying to learn something new from a con artist. Sure, they might actually tell you the truth, bu…

My experience has been that the hallucinations in GPT4 are actually pretty rare. But in any case, if I choose to use code it suggests I ask it for explanations and then I verify those myself by other means, e.g. tests. I think it's too strong to call it a really bad TA. I'd say it's an imperfect TA and you need to check it's work, but it's work still has great value.

It's not just things that can be caught with tests. You wouldn't know if you got recommended an obsolete API, a dated pattern, or a charged foot gun, and if you're looking up docs for every suggestion I doubt that'd save you much time compared to reading docs through to begin with.

Re: I won't deliberately use AI for programming

#40
post #10

I do so many things manually that have been successfully automated for a long time. Washing dishes, splitting firewood, grinding coffee, owning manual transmission cars, I could go on. Some things are subjectively better like splitting firewood; It's more work but quieter. Some things are objectively better; washing dished by hand are cleaner. I don't think about it too much. I guess I'll just add programming to that…

washing dishes by hand are absolutely NOT cleaner and ultimately extremely wasteful in terms of water used. use a dishwasher from the last 20 years.

Clearly you have not seen the dishwasher in my apartment. Trust me, washing by hand is more effective.
Post reply on HN