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

Tips for programmers to stay ahead of generative AI

spectrum.ieee.org

Post reply on HN
Print view View original

201–210 of 319 posts

Re: Tips for programmers to stay ahead of generative AI

#201

Post by kromem »

medler wrote: post #15

I use LLM-based autocomplete in my IDE, and it’s not taking away my job unless/until it improves by multiple orders of magnitude. It’s good at filling in boilerplate, but even for that I have to carefully check its output because it can make little errors even when I feel like what I want should be obvious. The article is absolutely correct in saying you have to be critical of its output. I would say it improves my p…

Oh, it will improve by several orders of magnitude.

But even then, it's not 'replacing' you.

It's just going to let you spend less time on BS and more time on the things that are your maximal value contributions to a project.

If I had a dozen junior or mid level devs you could hand work off to, would that save you time? Would you kick back and not review what they were doing, particularly around business critical parts of the software?

The conversation around AI has become obscenely binary, pulling from (now obsolete) SciFi influences to cast it as humans vs machines.

But it's a false dichotomy. Collaborative efforts are almost certainly where this is going, and 100% human or 100% AI will both be significantly inferior to a mix of both.

Re: Tips for programmers to stay ahead of generative AI

#202

Post by laeri »

I use ai mostly for creating code examples for specific things I haven't written before and for learning new programming languages.

During day to day I haven't used copilot or tabnine yet but I have seen that there exists some plugin I could integrate into neovim which I will definitely try.

Re: Tips for programmers to stay ahead of generative AI

#203

Post by afpx »

miki_tyler wrote: post #130
teaearlgraycold wrote: post #128

Earlier quoted context omitted.

What's the problem with hallucinations when your editor can tell you automatically if the code compiles or not?

Sometimes the hallucinations compile.

Have it write the unit tests first.

Re: Tips for programmers to stay ahead of generative AI

#204

Post by kromem »

wouldbecouldbe wrote: post #62
arrowsmith wrote: post #53

Earlier quoted context omitted.

I find it increases my productivity about 5-10% when working with the technologies I'm the most familiar with and use regularly (Elixir, Phoenix, JavaScript, general web dev.) But when I'm doing something unfamiliar and new, it's more like 90%. It's incredible. Recently at work, for example, I've been setting up a bunch of stuff with some new technologies and libraries that I'd never really used before. Without ChatG…

The thing is the hallucinations, I also wasted few hours trying to work on solutions with GPT where it just kept making up parameters and random functions.

Integration with linters is going to be the next stage in generative coding.

It should suggest, lint the suggestion in the background, and if it passes offer the suggestion and if not provide the linting issues output to rework the suggestion.

In general, token costs going down will in turn increase the number of multi-pass generation systems over single-pass systems, which is going to improve dramatically.

Combine all that with persistent memory storages that can provide in-context additional guidance around better working with your codebase and you, and it's going to be quite a different experience than it is today.

And at the current rate of advancement, that's maybe going to be how things will look within a year or two.

Re: Tips for programmers to stay ahead of generative AI

#205

Post by easeout »

bandrami wrote: post #200

The people who can use AI to make code are the same people who can write code. I've never really seen how this is supposed to expand the dev base.

It doesn't seem so different from what higher level languages becoming the norm has done year by year. You still benefit from knowing what's going on under the hood, but it's not strictly necessary, and lots of newer folks in software careers get by without ever really looking behind the curtain. My web dev colleagues barely touch a debugger.

Re: Tips for programmers to stay ahead of generative AI

#206

Post by kromem »

yayitswei wrote: post #48
medler wrote: post #15

I use LLM-based autocomplete in my IDE, and it’s not taking away my job unless/until it improves by multiple orders of magnitude. It’s good at filling in boilerplate, but even for that I have to carefully check its output because it can make little errors even when I feel like what I want should be obvious. The article is absolutely correct in saying you have to be critical of its output. I would say it improves my p…

I agree with 5%. That said, I've found rubber duck debugging to be an exceptionally effective use case for ChatGPT. Often it will surprise me by pinpointing the solution outright, but I'll always be making progress by clarifying my own thinking.

Yeah, it's an amazing rubber duck.

Even in the IDE I'll sometimes just write comments like (arbitrary example out of thin air):

// Q: Should we use a for loop or a while loop here? // A:

It doesn't always have a great answer, but as you say, it almost always helps my own thinking about it, which is often much more valuable.

Re: Tips for programmers to stay ahead of generative AI

#207

Post by SergeAx »

I recently tried to write a simple classificator using pytorch with ChatGPT. I found out that I cannot use the recent version of pytorch, but only the one was in use before ChatGPT knowledge cutoff. That also meant that I was limited by using Python 3.9, because most September 2021 libraries had no readily available builds for 3.10+.

And this is quite particular example. Software evolves quickly, ML models are expensive to train, and the gap will be mostly there anyway.

Re: Tips for programmers to stay ahead of generative AI

#208

Post by SergeAx »

twodave wrote: post #121

Is programming even the hard part about programming? In all seriousness, what we would really need from an AI to start really saving me time would be for it to interview all the customers/partners involved on the project, determine the scope of function needed, boil all that down to a set of sensible domain models that make sense to everyone, identify where/when messages need to be passed, determine which things can…

You understand that your generated code is from September 2021 at best, right? Maybe it's okay for some niches, but I see lots of evolution in almost all segments of software engineering, especially frontend and ML.

Re: Tips for programmers to stay ahead of generative AI

#209

Post by yayitswei »

hn_user82179 wrote: post #157
yayitswei wrote: post #48

Earlier quoted context omitted.

I agree with 5%. That said, I've found rubber duck debugging to be an exceptionally effective use case for ChatGPT. Often it will surprise me by pinpointing the solution outright, but I'll always be making progress by clarifying my own thinking.

Fascinating! Can I ask how you use ChatGPT for debugging? are the bugs you've used it with more high level, "this is what's happening" kind of things? Or could you give an example?

It's similar to how you would describe a problem to a coworker on Slack. I give it some context, then I state the problem or paste in the error message/stacktrace. I might also list steps that I've taken already. Then I follow ChatGPT's suggestions to troubleshoot. Sometimes I need to supplement with my own ideas, but usually that's enough to iteratively bisect the issue.

Re: Tips for programmers to stay ahead of generative AI

#210

Post by justanotherunit »

steve_adams_86 wrote: post #165

I’m an okay programmer, but I get my contracts by being able to understand what my client needs and assuring them I can find the right people, do the right work, and complete a project on time and within their budget. They pick me because I have solid references, I’m kind to them (I’m genuinely grateful for the relationships I build), I listen well, and I prioritize their experience over my convenience. I’m able to t…

I agree, it feels like coding is starting to become somewhat easier since AI can both explain and generate code snippets okay, and is improving over time. So the good old days of just creating an innovative program without major human interactions has passed.

Taking the customers requests and discussing into an suitable feature, without totally shooting down the idea and trying to explain why it won’t work is some of the harder parts of being a programmer these days, at least in my experience.

Post reply on HN