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

561–570 of 1001 posts

Re: A coder considers the waning days of the craft

#561

Post by BlueTemplar »

flir wrote: post #501
miiiiiike wrote: post #447

Earlier quoted context omitted.

I’d need to see it. I can’t get ChatGPT to outperform a novice. And now I’m having candidates argue that they don’t need to learn the fundamentals because LLMs can do it for them.. Good luck HTML/CSS expert who couldn’t produce a valid HTML5 skeleton. Reminds me of the pre-LLM guy who said he was having trouble because usually uses React.. So I told him he could use React. I don’t mean to rag on novices but these guy…

I'm always asking it to stitch together ad hoc bash command lines for me, eg "find all the files called *.foo in directories called bar and search them for baz". (`find / -type d -name 'bar' -exec find {} -type f -name '*.foo' \; | xargs grep 'baz'` apparently.) I would have done that differently, but it's close enough for government work.

Except you should at least try to write code for someone else (and probably of lower level of competence - this also helps for your own debugging later) - obscure one-liners like these should be rejected.

Re: A coder considers the waning days of the craft

#562

Post by girvo »

chalcolithic wrote: post #331
corethree wrote: post #288

Earlier quoted context omitted.

>Maybe I’m in the minority. I’m definitely extremely impressed with GPT4, but coding to me was never really the point of software development. You're not the minority. You're the majority. The majority can't look reality in the face and see the end. They lie to themselves. >While GPT4 is incredible, it fails OFTEN. And it fails in ways that aren’t very clear. And it fails harder when there’s clearly not enough traini…

I'm used to HN being sensible, and seeing your comment being downvoted makes me wonder what's happening? What's the reason for that optimism?

HN’s culture has changed somewhat and downvotes are now used more often to signal disagreement, sadly. But also “use common sense” and “but the trendline” are only partially compelling arguments as presented if you already believe what is being argued. They’re not compelling enough to those who aren’t convinced yet

Re: A coder considers the waning days of the craft

#563

Post by anonzzzies »

eloisant wrote: post #547
anonzzzies wrote: post #535

Earlier quoted context omitted.

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…

If it can pass it when you ask it in a way only a coder can write, then we will still need coders. If you need to tweak your prompt until you get the correct result, then we still need coders who can tell that the code is wrong. Ask Product Managers to use ChatGPT instead of coders and they will ask for 7 red lines all perpendicular to each other with one being green. https://www.youtube.com/watch?v=BKorP55Aqvg

I didn't say we don't need coders. We need less average/bad ones and a very large amounts of coders that came after the 'coding makes $$$$' worldwide are not even average.

I won't say AI will not eventually make coding obsolete; even just 2 years ago I would've said we are 50-100 years away from that. No i'm not so sure. However, I am saying that I can replace many programmers with gpt right now, and I am. The prompting and reprompting is still both faster and cheaper than many humans.

Re: A coder considers the waning days of the craft

#564

Post by wokwokwok »

throwaway346434 wrote: post #537
mrtksn wrote: post #461

Earlier quoted context omitted.

Try breaking down the problem. You don't have to do it yourself, you can tell ChatGPT to break down the problem for you then try to implement individual parts. When you have something that kind of works, tell ChatGPT what the problems are and ask for refinement. IMHO currently the weak point of LLMs is that they can't really tell what's adequate for human consumption. You have to act as a guide who knows what's good…

... 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…

The output of an LLM is a distribution, and yes, if you’re just taking the first answer, that’s problematic.

However, it is a distribution, and than means the majority of solutions are not weird edge cases, they’re valid solutions.

Your job as a user is to generate multiple solutions and then review them and pick the one you like the most, and maybe modify it to work correctly if it has weird edge cases.

How do you do that?

Well, you can start by following a structured process where you define success criteria as a validator (eg. Tests, compiler, parser, linters) and fitness criteria as a scorer (code metrics like complexity, runtime, memory use, etc)… then:

1) define goal

2) generate multiple solution candidates

3) filter candidates by validator (does it compile? Pass tests? Etc)

4) score the solutions (is it pure? Is it efficient? Etc)

5) pick the best solution

6) manually review and tweak the solution

This structured and disciplined approach to software engineering works. Many of the steps (eg. 3, 4, 5) can be automated.

It generates meaningful quality code results.

You can use it with or without AI…

You don’t have to follow this approach, but my point is that you can; there is nothing fundamentally intractable able using a language model to generate code.

The problem that you’re critiquing is the trivial and naive approach of just hitting “generate” and blindly copying that into your code base.

…that’s stupid and dangerous, but it’s also a straw man.

Seriously; people writing code with these models aren’t doing that; when you read blogs and posts from people, eg. Building seriously using copilot you’ll see this pattern emerge repeatedly:

Generate multiple solutions. Tweak your prompt. Ask for small pure dependency free code blocks. Review the and test output.

It’s not a dystopian AI future, it’s just another tool.

Re: A coder considers the waning days of the craft

#565

Post by lom »

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…

You’re missing the point of the article. ChatGPT in combination with a mediocre could solve your problem faster than the best junior dev has before

Re: A coder considers the waning days of the craft

#566

Post by borissk »

hackerlight wrote: post #481
jeffreygoesto wrote: post #343

Earlier quoted context omitted.

Not necessarily. Every hockey stick is just the beginning of an s-curve. It will saturate, probably sooner than you think.

Some parts of AI will necessarily asymptote to human-level intelligence because of a fixed corpus of training data. It's hard to think AI will become a better creative writer than the best human creative writers, because the AI is trained on their output and you can't go much further than that. But in areas where there's self-play (e.g. Chess, and to a lesser extent, programming), there is no good reason to think it'…

So you think human readers have magical powers to rate say a book that an AI can't replicate?

Re: A coder considers the waning days of the craft

#567

Post by spaceman_2020 »

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…

Would you mind sharing the test?

I’m one of those noob programmers and it has helped me create products far beyond my technical capabilities

Re: A coder considers the waning days of the craft

#568

Post by digitcatphd »

datpiff wrote: post #555
digitcatphd wrote: post #487

Earlier quoted context omitted.

> It answers questions confidently but with subtle inaccuracies. This is a valid challenge we are facing as well. However, remember that ChatGPT which many coders use, is likely training on interactions so you have some human reinforcement learning correcting its errors in real-time.

How is it trained on reactions? Do people give it feedback? In my experience in trying I stop asking when it provides something useful or something so bad I give up (usually the latter I'm afraid). How would it tell a successful answer from a failing one?

It appears to ask users to rate if the response is better or worse than the first, in other cases, it seems to be A/B testing the response. Lastly, I for instance, will correct it and then confirm it is correct to continue with the next task, which likely creates a footprint pattern.

Re: A coder considers the waning days of the craft

#569

Post by sean_the_geek »

My two cents having used AI in programming. It is merely a tool to create. It is not the creator yet, at least in its current iteration.

AI is to programming what electric drill were to wood working before they were invented. It made life easy; it sped up the process and may be it did a job a bit finer. But you still need to understand where to drill and how to create the thing. There are a number of analogies like this you can find.

Re: A coder considers the waning days of the craft

#570

Post by theonlybutlet »

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…

Push comes to shove, it always tends to come down to short term cost. If it gets the job done, and it's wildly cheaper than the status quo (Net Present Value savings). they'll opt for it.

The only reason the trucks aren't out there gathering their best data, that's real world data, is regulation.

Businesses will hire consultants at a later stage to do risk assessment and fix their code base.

Post reply on HN