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

121–130 of 319 posts

Re: Tips for programmers to stay ahead of generative AI

#121

Post by twodave »

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 happen piecemeal as opposed to requiring a bulk op, deciding on a persistence technology based on the nature of the requirements...

And that's just an abbreviated form of what I go through when designing a back-end for a tiny boutique application. 99% of programming is making decisions. When you finally have everything planned, the code can almost write itself, but getting to that point requires so much background knowledge that I'm not sure GPT4 will be hunting for my job anytime soon. Or even really augmenting it. I'd be happier if they could just get auto-complete in VS Code to not suck complete balls.

Re: Tips for programmers to stay ahead of generative AI

#122

Post by davewritescode »

arrowsmith wrote: post #53
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 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…

This is what ChatGPT and GPT4 are good for, iterating quickly in an unfamiliar ecosystem. Picking up frameworks now feels like a ChatGPT superpower. It doesn't remove reasoning and I've seen some scary bugs introduced if you're not really carefully monitoring what the AI is outputting.

Basically, these days before I dig into documentation I ask "How do I do X with Y framework in Language Z" and if it's pre-2021 tech it works amazingly well.

Re: Tips for programmers to stay ahead of generative AI

#123

Post by davewritescode »

tehwebguy wrote: post #72
wouldbecouldbe wrote: post #62

Earlier quoted context omitted.

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.

It referenced a made up a function I needed (that should probably exist lol) in BrightScript, the letdown after realizing as much was painful.

This is the WORST feeling if you use co-pilot in an IDE. It's so incredibly disappointing.

Re: Tips for programmers to stay ahead of generative AI

#124

Post by ukuina »

DonaldPShimoda wrote: post #56
Kiro wrote: post #10

Earlier quoted context omitted.

Read the next sentence after your quote. The point is that you should include code and examples in your prompt (Copilot is so good since it includes the surrounding code and open files in the prompt to understand your specific context), not that you should craft an exceptional "act as rockstar engineer" prompt.

I did read it, but the whole premise is flawed due to an apparently incomplete understanding of how LLMs work. Including code samples in your prompt won't have the effect you think it will. LLMs are trained to produce results that are statistically likely to be syntactically well-formed according to assumptions made about how "language" works. So when you provide code samples, the model incorporates those into the re…

I think this is incorrect for most use-cases. LLMs do grok code semantically. Adding requests for coding style injects implementation specificity when flattening the semantic multidimensionality back into language.

Re: Tips for programmers to stay ahead of generative AI

#125

Post by twodave »

For all the folks out there saying, "Wow this will enable so many more people to become proficient at programming!" Just stop. The last couple of decades the likes of Google and the rest of the FAANG/whatever acronym you want to put on it have been standing on the street corner screaming, "PASS A LEET CODE INTERVIEW AND WE WILL MAKE YOU RICH." ChatGPT has nothing even close to that amount of incentive attached to it. I see LLMs helping middling developers accomplish things in code that they'd otherwise be slower at or unable to complete. Or in a different language. Doing things faster pretty much implies a lower level of understanding, which means maintenance costs (which are already the majority of costs for most companies) will only increase. There is so much more incentive to spend on R&D, and using an LLM to iterate faster can actually skew costs in the wrong direction.

Re: Tips for programmers to stay ahead of generative AI

#126

Post by epylar »

skeeter2020 wrote: post #96
OwenFM wrote: post #92

If people get left behind, it mightn't be such a bad thing − the cheaper software will lower the cost of living, making UBI more feasible. The glut of unemployed people will hopefully popularise UBI rather than trying to jump back on the treadmill of GDP maximisation, exploiting each other and destroying our planet. https://nonhuman.party/post/replacing_capitalism/

Interesting take, ignoring the fact there will be far less people to pay into your magical UBI pool. How do you reconcile a huge glut of unemployed people and the resources to hand out extensive welfare benefits?

I think the idea behind UBI is the corporations will pay most of the taxes required.

Re: Tips for programmers to stay ahead of generative AI

#127

Post by teaearlgraycold »

davewritescode wrote: post #122
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…

This is what ChatGPT and GPT4 are good for, iterating quickly in an unfamiliar ecosystem. Picking up frameworks now feels like a ChatGPT superpower. It doesn't remove reasoning and I've seen some scary bugs introduced if you're not really carefully monitoring what the AI is outputting. Basically, these days before I dig into documentation I ask "How do I do X with Y framework in Language Z" and if it's pre-2021 tech…

Especially when you know something similar. Like porting between front-end frameworks. Just sketch out some React code and ask it to port to Vue - you can even tell it to explain the Vue code line-by-line and ask follow up questions, ex "Oh, so $FEATURE is like hooks in React?" "Yes, but ..."

Re: Tips for programmers to stay ahead of generative AI

#128

Post by teaearlgraycold »

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.

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

Re: Tips for programmers to stay ahead of generative AI

#129

Post by klysm »

robbomacrae wrote: post #114

If you haven't already I urge you to try getting ChatGPT4 to do most of your programming for you. Just ask it interview style coding questions and refine the answer with more interview like follow on questions. And for making changes to existing code, you might need to check with your company's policies on this, but if you're ok to paste code into ChatGPT you can also just ask how to change it to do Y instead of X. C…

I’m not putting anything with important IP into chatgpt

Re: Tips for programmers to stay ahead of generative AI

#130

Post by miki_tyler »

teaearlgraycold wrote: post #128
wouldbecouldbe wrote: post #62

Earlier quoted context omitted.

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.

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

Sometimes the hallucinations compile.
Post reply on HN