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

A coder considers the waning days of the craft

newyorker.com

Post reply on HN
Print view View original

631–640 of 1001 posts

Re: A coder considers the waning days of the craft

#631

Post by CaptainFever »

simonw wrote: post #176

> What I learned was that programming is not really about knowledge or skill but simply about patience, or maybe obsession. Programmers are people who can endure an endless parade of tedious obstacles. This captures the reason I'm optimistic about AI-assisted programming. The learning curve for getting started programming is horribly steep - and it's not because it's hard, it's because it's frustrating. You have to s…

> I think LLMs dramatically impact that initial learning curve. I love the idea that many more people will be able to learn basic programming - I think every human being deserves to be able to use computers to automate tedious repetitive tasks in their lives.

This honestly made me feel so happy. I'm reminded of the average person who is bound by the limitations of the apps they use, the popularity of "How to Automate Using Python" books...

With this new tech, people are no longer bound by that limitation. I think that's pretty cool.

Re: A coder considers the waning days of the craft

#632

Post by barrkel »

ern wrote: post #444
miiiiiike wrote: post #409

I have a simple front-end test that I give to junior devs. Every few months I see if ChatGPT can pass it. It hasn’t. It can’t. It isn’t even close. It answers questions confidently but with subtle inaccuracies. The code that it produces is the same kind of non-sense that you get from recent bootcamp devs who’ve “mastered” the 50 technologies on their eight page résumé. If it’s gotten better, I haven’t noticed. Self-d…

I was on a team developing a critical public safety system on a tight deadline a few years ago, and i had to translate some wireframes for the admin back-end into CSS. I did a passable job but it wasn’t a perfect match. I was asked to redo it by the team-lead. It had zero business value, but such was the state of our team…being pixel perfect was a source of pride. It was one of the incidents that made me to stop fron…

ChatGPT goes from zero to maybe 65th percentile? There or thereabouts. It's excellent if you know nothing. It's mediocre and super buggy if you're an expert.

A big difference is that the expert asks different questions, off in the tails of the distribution, and that's where these LLMs are no good. If you want a canonical example of something, the median pattern, it's great. As the ask heads out of the input data distribution the generalization ability is weak. Generative AI is good at interpolation and translation, it is not good with novelty.

(Expert and know-nothing context dependent here.)

One example: I use ChatGPT frequently to create Ruby scripts for this and that in personal projects. Frequently they need to call out other tools. ChatGPT 4 consistently fails to properly (and safely!) quote arguments. It loves the single-argument version of system which uses the shell. When you ask it to consider quoting arguments, it starts inserting escaped quotes, which is still unsafe (what if the interpolated variable contains a quote in its name). If you keep pushing, it might pull out Shell.escape or whatever it is.

I assume it reproduces the basic bugs that the median example code on the internet does. And 99% of everything being crap, that stuff is pretty low quality, only to be used as an inspiration or a clue as to how to approach something.

Re: A coder considers the waning days of the craft

#633

Post by TMWNN »

yonisto wrote: post #341

I'm currently re-writing a GPT4 code which is a very interesting experience. The biotech startup I join 3 months ago have a pipeline written by one of the founders, who has experience in programing but not extensive so he used co-pilot and GTP a lot. The thing WORKS, it actually delivers! this is what got the startup going so it is amazing. On the first month of the re-write I was able to cut costs in the 100x mark.…

>The biotech startup I join 3 months ago have a pipeline written by one of the founders, who has experience in programing but not extensive so he used co-pilot and GTP a lot. The thing WORKS, it actually delivers! this is what got the startup going so it is amazing.

Indeed!

>On the first month of the re-write I was able to cut costs in the 100x mark.

That's clearly where this is all heading: AI delivering the rough draft, and humans applying what AI inevitably misses.

>And on the third month I was able to uncover some subtle bugs that affect the entire pipeline and fixing them is out of the realm of possibility in the current state of AI.

It's entirely possible that had you or another human written the thing in the first place those bugs (or equivalent thereof) would have still been there. As you said, "subtle".

>I have no answer whatever employers will continue to value what I bring to the table in 5/10/15 years time especially after AI will improve. I suspect many will not as they will have 'good enough' results from the AI.

I would be more optimistic based on your own account, for the reasons I mentioned above.

That said, I am glad that I am self-employed, with a business that I am quite confident AI cannot replicate, and code purely for fun.

Re: A coder considers the waning days of the craft

#634

Post by giantg2 »

winrid wrote: post #199
giantg2 wrote: post #195

Earlier quoted context omitted.

Every time I hear coding referred to as a craft I sort of hate it. On one hand I love the idea of it being a highly skilled craft - knowing the intricacies of the language and the machine to solve any problem, being a respected expert, producing a product worthy of pride. On the other hand, most of what we do is display [some content] on [some page] (probably sloppily due to deadlines), or print 100 random entries fr…

well, in that regard you're a fancy carpenter assembling IKEA dressers. Carpentry is still a craft.... most people just need IKEA. :)

Not really. My skills have drastically declined over the years because I rarely get a chance to exercise them. On top of that, it seems I'm switching languages/stacks frequently. So it's more like I'm a carpenter for a little while, then a plumber, then an electrician.

Re: A coder considers the waning days of the craft

#635

Post by timcobb »

matheusmoreira wrote: post #262
skepticATX wrote: post #82

Am I the only one becoming less impressed by LLMs as time passes? I will admit, when Copilot first became a thing in 2021, I had my own “I’m about to become obsolete” moment. However, it’s become clear to me, both through my own experience and through research that has been conducted, that modern LLMs are fundamentally flawed and are not on the path to general intelligence. We are stuck with ancient (in AI terms) tec…

> Am I the only one becoming less impressed by LLMs as time passes? Not at all. I was very impressed at first but it's gotten to the point where I can no longer trust anything it says other than very high level overviews. For example, I asked it to help me implement my own sound synthesizer from scratch. I wanted to generate audio samples and save them to wave files. The high level overview was helpful and enabled me…

> It's pretty great at reducing the loneliness of solo programming though. Just bouncing ideas and seeing what it says helps a lot. It's not like other people would want to listen.

Re: A coder considers the waning days of the craft

#636

Post by gumballindie »

mrtksn wrote: post #546
throwaway346434 wrote: post #537

Earlier quoted context omitted.

... What. It hallucinates and it doesn't compile, fine. It hallucinates and flips a 1 with a -1; oops that's a lot of lost revenue. But it compiled, right? It hallucinates, and in 4% of cases rejects a home loan when it shouldn't because of a convoluted set of nested conditions, only there is no one on staff that can explain the logic of why something is laid out the way it is and I mean, it works 96% of the time so…

As I said, you are still responsible for the quality control. You are supposed to notice that everyone is named Dave and tell ChatGPT to fix it. Write tests, read code, run & observe for odd behaviours. It's not an autonomous agent just yet.

But why should i waste time using a broken product when i can do it properly myself? To me a lot of this debate sounds like people obsessively promoting a product for some odd reason, as if they were the happy owners of a hammer in search of a nail.

Re: A coder considers the waning days of the craft

#637

Post by steveBK123 »

miiiiiike wrote: post #409

I have a simple front-end test that I give to junior devs. Every few months I see if ChatGPT can pass it. It hasn’t. It can’t. It isn’t even close. It answers questions confidently but with subtle inaccuracies. The code that it produces is the same kind of non-sense that you get from recent bootcamp devs who’ve “mastered” the 50 technologies on their eight page résumé. If it’s gotten better, I haven’t noticed. Self-d…

That's been my experience both with Tesla AP/FSD implementation & with LLMs.

Super neat trick the first time you encounter it, feels like alien tech from the future.

Then you find all the holes. Use it for months/years and you notice the holes aren't really closing.. The pace of improvement is middling compared to the gap to it meeting the marketing/rhetoric. Eventually using them feels more like a chore than not using them.

It's possible some of these purely data driven ML approaches don't work for problems you need to be more than 80% correct on.

Trading algos that just need to be right 55% of the time to make money, recommendation engines that present a page of movies/songs for you to scroll, Google search results that come back with a list you can peruse, Spam filters that remove some noise from your inbox.. sure.

But authoritative "this is the right answer" or "drive the car without murdering anyone".. these problems are far harder.

Re: A coder considers the waning days of the craft

#639

Post by CaptainFever »

rukuu001 wrote: post #608
lysecret wrote: post #591

So, a few months ago I wanted to lose some weight and wanted to count my calories. As a coder would, I thought why not build a swift app that uses the ChatGPT API to count them (instead of doing it the boring way). I'm a fairly experienced backend dev I built a few toy websites and I am casually interested in frontend stuff (like watching Fireship) so I thought I'd give it a try. Long story short, it worked well. I h…

> But yes, my overall experience is that I think we are in for an exciting new time, but we are lacking a new coding paradigm. This is the big one for me. I feel like we're all having "640K ought to be enough for anybody" type conversations right now.

640K tokens ought to be enough for anybody

Re: A coder considers the waning days of the craft

#640

Post by Exuma »

anonzzzies wrote: post #535
miiiiiike wrote: post #409

I have a simple front-end test that I give to junior devs. Every few months I see if ChatGPT can pass it. It hasn’t. It can’t. It isn’t even close. It answers questions confidently but with subtle inaccuracies. The code that it produces is the same kind of non-sense that you get from recent bootcamp devs who’ve “mastered” the 50 technologies on their eight page résumé. If it’s gotten better, I haven’t noticed. Self-d…

So, don't leave us in suspense; what do you ask of it? Because I'm quite sure it can already pass it. Your experience is very different from mine anyway. I am a grumpy old backend dev that uses formal verification in anger when I consider it is needed and who gets annoyed when things don't act logical. We are working with computers, so everything is logical, but no; I mean things like a lot of frontend stuff. I ask o…

How do you make a custom gpt which knows a specific code base? I have been wanting to do this
Post reply on HN