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

Don't fall into the anti-AI hype

antirez.com

Post reply on HN
Print view View original

831–840 of 1001 posts

Re: Don't fall into the anti-AI hype

#831

Post by tripzilch »

khafra wrote: post #667
totallykvothe wrote: post #569

I don't understand the stance that AI currently is able to automate away non-trivial coding tasks. I've tried this consistently since GPT 3.5 came out, with every single SOTA model up to GPT 5.1 Codex Max and Opus 4.5. Every single time, I get something that works, yes, but then when I start self-reviewing the code, preparing to submit it to coworkers, I end up rewriting about 70% of the thing. So many important deta…

> Non-trivial coding tasks A coding agent just beat every human in the AtCoder Heuristic optimization contest. It also beat the solution that the production team for the contest put together. https://sakana.ai/ahc058/ It's not enterprise-grade software, but it's not a CRUD app with thousands of examples in github, either.

had to scroll far to find the problem description

> AHC058, held on December 14, 2025, was conducted over a 4-hour competition window. The problem involved a setting where participants could produce machines with hierarchical relationships, such as multiple types of “apple-producing machines” and “machines that build those machines.” The objective was to construct an efficient production planning algorithm by determining which types and hierarchies of machines to upgrade and in what specific order.

... so not a CRUD app but it beat humans at Cookie Clicker? :-)

Re: Don't fall into the anti-AI hype

#832

Post by antfarm »

I was against AI-assisted coding until I started a pet iOS project and used Claude (Code) Desktop to have someone to discuss my architecture and design decisions with. At first, I only accepted code snippets that I copy/pasted myself, but with Claude Code`s use of git worktrees I now more often trust Claude to edit my code.

I review every single line and keep the increments small. I also commit often. Wouldn't want to go back to coding alone.

Re: Don't fall into the anti-AI hype

#833

Post by Cthulhu_ »

zeroonetwothree wrote: post #311
embedding-shape wrote: post #95

> But what was the fire inside you, when you coded till night to see your project working? It was building. I feel like this is not the same for everyone. For some people, the "fire" is literally about "I control a computer", for others "I'm solving a problem for others", and yet for others "I made something that made others smile/cry/feel emotions" and so on. I think there is a section of programmer who actually do…

You’re right of course. For me there’s no flow state possible with LLM “coding”. That makes it feel miserable instead of joyous. Sitting around waiting while it spits out tokens that I then have to carefully look over and tweak feels like very hard work. Compared to entering flow and churning out those tokens myself, which feels effortless once I get going. Probably other people feel differently.

I gotta say, the "sitting around waiting" comment hits - I have the same with current-day merge request based development, a lot of time is fragmented because I'm waiting for the CI to finish. I've got seven open merge requests at the moment, some of which have been open since before the holidays. It's a lot of fragmented waiting, fixing, prodding people to review code, and shitposting on HN to pass the time. It's uh. Not healthy.

But this is my reality in my current line of work, a lot of relatively simple work but a lot of processes and checks to conform to rules (that I set myself lol) and not break existing functionality.

Re: Don't fall into the anti-AI hype

#834

Post by theshrike79 »

febusravenga wrote: post #777
simonw wrote: post #160

Earlier quoted context omitted.

This is a pretty common position: "I don't worry about getting left behind - it will only take a few weeks to catch up again". I don't think that's true. I'm really good at getting great results out of coding agents and LLMs. I've also been using LLMs for code on an almost daily basis since ChatGPT's release on November 30th 2022. That's more than three years ago now. Meanwhile I see a constant flow of complaints fro…

> Using this stuff well is a deep topic. These things can be applied in so many different ways, and to so many different projects. The best asset you can develop is an intuition You're basically saying that using LLMs is like using magic. Telling people to use intuition is basically telling that i don't know how it works and why, but works for me sometimes. That's why we programmers hate it - we have safe space where…

It's like any other power tool. It requires skill to use it safely and efficiently.

Anyone can use a band saw to cut things. Then go look what Jimmy DiResta makes with one and you see the difference.

The chance of an inexperienced person cutting off their finger with a bandsaw is also way over zero, there are things you should not and must not do with it. As with any power tool.

Re: Don't fall into the anti-AI hype

#835

Post by jstummbillig »

totallykvothe wrote: post #569

I don't understand the stance that AI currently is able to automate away non-trivial coding tasks. I've tried this consistently since GPT 3.5 came out, with every single SOTA model up to GPT 5.1 Codex Max and Opus 4.5. Every single time, I get something that works, yes, but then when I start self-reviewing the code, preparing to submit it to coworkers, I end up rewriting about 70% of the thing. So many important deta…

> Every single time [...] I end up rewriting about 70% of the thing

If that number has not significantly changed since GPT 3.5, I think it's safe to assume that something very weird is happening on your end.

Re: Don't fall into the anti-AI hype

#836

Post by lelanthran »

ahmadyan wrote: post #770
gspr wrote: post #767

Earlier quoted context omitted.

I still really, really, really struggle to see how humans are going to maintain and validate the programs written by LLMs if we no longer know (intimately) how to program. Any thoughts?

Very few people have the expertise to write efficient assembly code, yet everyone relies on compilers and assemblers to translate high-level code to byte-level machine code. I think same concept is true here. Once coding agents become trivial, few people will know the detail of the programming language and make sure intent is correctly transformed to code, and the majority will focus on different objectives and take…

> Very few people have the expertise to write efficient assembly code, yet everyone relies on compilers and assemblers to translate high-level code to byte-level machine code. I think same concept is true here.

That's a poor analogy which gets repeated in every discussion: compilers are deterministic, LLMs are not.

Re: Don't fall into the anti-AI hype

#837

Post by xmodem »

eloisant wrote: post #825
totallykvothe wrote: post #569

I don't understand the stance that AI currently is able to automate away non-trivial coding tasks. I've tried this consistently since GPT 3.5 came out, with every single SOTA model up to GPT 5.1 Codex Max and Opus 4.5. Every single time, I get something that works, yes, but then when I start self-reviewing the code, preparing to submit it to coworkers, I end up rewriting about 70% of the thing. So many important deta…

You can definitely use AI for non-trivial tasks. It's not just about better prompting, but using better tools. Tools that will turn a bad prompt into a good prompt. For example there is the plan mode for Cursor. Or just ask the AI: "make a plan to do this task", then you review the plan before asking it to implement. Configure the AI to ask you clarification questions instead of assuming things. It's still evolving p…

I have not been as aggressive as GP in trying new AI tools. But the last few months I have been trying more and more and I'm just not seeing it.

One project I tried out recently I took a test-driven approach. I built out the test suite while asking the AI to do the actual implementation. This was one of my more successful attempts, and may have saved me 20-30% time overall - but I still had to throw out 80% of what it built because the agent just refused to implement the architecture I was describing.

It's at its most useful if I'm trying to bootstrap something new on a stack I barely know, OR if I decide I just don't care about the quality of the output.

I have tried different CLI tools, IDE tools. Overall I've had the best success with Claude Code but I'm open to trying new things.

Do you have any good resources you would recommend for getting LLM's to perform better, or staying up-to-date on the field in general?

Re: Don't fall into the anti-AI hype

#838

Post by dspillett »

antirez wrote: post #745
totallykvothe wrote: post #569

I don't understand the stance that AI currently is able to automate away non-trivial coding tasks. I've tried this consistently since GPT 3.5 came out, with every single SOTA model up to GPT 5.1 Codex Max and Opus 4.5. Every single time, I get something that works, yes, but then when I start self-reviewing the code, preparing to submit it to coworkers, I end up rewriting about 70% of the thing. So many important deta…

After you review, instead of rewriting 70% of the code, have you tried to follow up with a message with a list of things to fix? Also: in my experience 1. and 2. are not needed for you to have bad results. The existing code base is a fundamental variable. The more complex / convoluted it is, the worse is the result. Also in my experience LLMs are constantly better at producing C code than anything else (Python includ…

> After you review, instead of rewriting 70% of the code, have you tried to follow up with a message with a list of things to fix?

This is one of my problems with the whole thing, at least from a programming PoV. Even though superficially it seems like the ST:TNG approach to using an intelligent but not aware computer as a tool to collaboratively solve a problem, it is really more like guiding a junior through something complex. While guiding a junior (or even some future AGI) in that way is definitely a good thing, if I am a good guide they will learn from the experience so it will be a useful knowledge sharing process, that isn't a factor for an LLM (at least not the current generations). But if I understand the issue well enough to be a good guide, and there is no teaching benefit external to me, I'd rather do it myself and at most use the LLM as a glorified search engine to help muddle through bad documentation for hidden details.

That and TBH I got into techie things because I like tinkering with the details. If I thought I'd not dislike guiding others doing the actual job, I'd have not resisted becoming a manager throughout all these years!

Re: Don't fall into the anti-AI hype

#839

Post by Cthulhu_ »

bossyTeacher wrote: post #421
zeroonetwothree wrote: post #311

Earlier quoted context omitted.

You’re right of course. For me there’s no flow state possible with LLM “coding”. That makes it feel miserable instead of joyous. Sitting around waiting while it spits out tokens that I then have to carefully look over and tweak feels like very hard work. Compared to entering flow and churning out those tokens myself, which feels effortless once I get going. Probably other people feel differently.

This. To me, using an LLMs is more like having a team of ghostwriters writing your novel. Sure, you "built" your novel but it feels entirely different to writing it yourself.

Wouldn't it be like having a team of software developers writing your code? The analogy doesn't need to be even as far as a different line of work. And for some this (writing to managing) is a natural career progression.

Re: Don't fall into the anti-AI hype

#840

Post by softwaredoug »

antirez wrote: post #747
softwaredoug wrote: post #718

If you’re getting started, in say Claude, some pointers that helped me Stay in plan mode most of the time. It will produce a step by step set of instructions - more context - for the LLM to execute the change. It’s the best place to exert detailed control over what will happen. Claude lets you edit it in a vim window. Think about testing strategy carefully. Connecting the feedback back into the LLM is what makes a lo…

Good points. Also: Force it to have clear metrics / observability on what it is doing. For instance the other day I wanted Claude to modify a Commodore 64 emulator, and I started saying it to implement an observability framework where as the emulator run, it can connect to a socket and ask for registers, read/write memory areas, check the custom chips status, set breakpoints, ... As you can guess, after this the work…

Thank you -

I have coded since 4th grade, and your post made me less depressed about my career. Maybe even a tad hopeful.

Post reply on HN