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

751–760 of 1001 posts

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

#751

Post by redox99 »

Madmallard wrote: post #739
redox99 wrote: post #679

Earlier quoted context omitted.

It sounds harsh but you're most likely using it wrong. 1) Have an AGENTS.md that describes not just the project structure, but also the product and business (what does it do, who is it for, etc). People expect LLMs to read a snippet of code and be as good as an employee who has implicit understanding of the whole business. You must give it all that information. Tell it to use good practices (DRY, KISS, etc). Add patt…

"The LLM should be able to determine if a task was completed successfully or not." Writing logic that verifies something complex requires basically solving the problem entirely already.

Situation A) Model writes a new endpoint and that's it

Situation B) Model writes a new endpoint, runs lint and build, adds e2e tests with sample data and runs them.

Did situation B mathematically prove the code is correct? No. But the odds the code is correct increases enormously. You see all the time how the Agent finds errors at any of those steps and fixes them, that otherwise would have slipped by.

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

#752

Post by darkwater »

on_the_train wrote: post #245

Another one of these sickening pieces. Framing opposition to an expensive tech that doesn't work as "anti". I tried letting the absolutely newest models write c++ today again. Gpt 5.1 and opus 4.5. single function with two or less input parameters, a nice return value, doing simple geometry with the glm library. Yes the code worked. But I took as long fixing the weird parts as it would have taken me myself. And I sti…

Your comment sounds like John Glenn's quote "Get the girl to check the numbers… If she says they’re good, I’m ready to go." about Katherine Johnson to double check the calculations done by the first computers used by NASA. At that time in history, it was probably accurate and the safest thing to do, but we all know how computer evolved from that time and now we don't have human calculators anymore but rather human checking the correctness of the written code that will do the actual calculations.

IMO the only rebuttal to this can be that LLMs are almost at their peak and there is not going to be any possible significant breakthrough or steady improvement in the next years, in which case they will never become "the new computers".

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

#753

Post by antirez »

agoodusername63 wrote: post #297

I never stop being amused that LLMs have made HN realize that many programmers are programmers for paychecks. Not for passion

I like programming, and I do write code all the times. But when there is to do something productive, it is very hard to justify that for my ego or passion I don't leverage AI and go N times faster only because I'm used to enjoy a given process. I try to also enjoy the other process not related to writing code: ideas and design.

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

#754

Post by KronisLV »

9dev wrote: post #720
KronisLV wrote: post #709

Earlier quoted context omitted.

> I end up rewriting about 70% of the thing. Doesn't match my experience, that figure is closer to about 20-40% to me, though a lot of those changes I want are possible by just further prompting OR turning to a different model, or adding some automated checks that promptly fail and the AI can do a few more loops of fixes. > Other people are just less picky than I am, or they have a less thorough review culture that l…

> You can always be like: "This here pattern in these 20 files is Good Code™, use the same collection of approaches and code style when working on this refactoring/new feature." …and then add that to your CLAUDE.md, and never worry about having to say it again manually.

Exactly! Unless you use something that doesn’t read CLAUDE.md, then you’d still just tell the model to read the file as a part of its work.

What helped me a bunch was having prebuild scripts (can be Bash, can be Python, can be whatever) for each of the architectural or style conventions I want to enforce. Tools like ESLint are also nice but focused a bit more on the code than architecture/structure.

Problems start when a colleague might just remove some of those due to personal preference without discussion but then you have other problems - in my experience, with proper controls in place AI will cause less issues and friction than people (ofc depending on culture fit).

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

#755

Post by friendzis »

unyttigfjelltol wrote: post #604
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 I’ve come back to the idea LLMs are super search engines. If you ask it a narrow, specific question, with one answer, you may well get the answer. For the “non-trivial” questions, there always will be multiple answers, and you’ll get from the LLM all of these depending on the precise words you use to prompt it. You won’t get the best answer, and in a complex scenario requiring highly recurs…

> But giving all the answers without strong guidance on non-trivial architectural points— entropy. LLMs churning independently quickly devolve into entropy.

Typical iterative-circular process "write code -> QA -> fix remarks" works because the code is analyzable and "fix" is on average cheaper than "write", therefore the process, eventually, converges on a "correct" solution.

LLM prompting is on average much less analyzable (if at all) and therefore the process "prompt LLM -> QA -> fix prompt" falls somewhere between "does not converge" and "convergence tail is much longer".

This is consistent with typical observation where LLMs are working better: greenfield implementations of "slap something together" and "modify well structured, uncoupled existing codebase", both situations where convergence is easier in the first place, i.e. low existing entropy.

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

#756

Post by CatsOnHats »

The company i work for is spending the equivalent of the yearly salary of a dozen engineers, worth of tokens per month. It recently surpassed our monthly cloud spend bill.

We have people who are running the same tasl 10 times in parallel and having one LLm write a prompt for another LLm to execute then sitting on their phone for an hour while they let the AI's battle it out. For tasks that should take 3 minutes. Then having another coding agent make a PR, update JIRA tickets, etc.

Frankly it blows my mind that so many developers have so little actual understanding of cost associated with AI.

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

#757

Post by matwood »

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…

Good points. I'm a 'solve the problem' person, so rarely get into language wars, editor wars, etc... I just don't care as long as the problem is solved in a way that meets the needs of the user.

I've worked with all the types, and no type is wrong. For example, I can certainly appreciate the PL researcher type who wants to make everything functional, etc... I won't fight against it as long as it doesn't get in the way of solving the problem. I've also found that my style works well with the other styles because I have way of always asking "so does this solve the problem??" which is sometimes forgotten by the code is beautiful people, etc...

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

#758

Post by antirez »

zephyrthenoble wrote: post #673

It was weird to read this. I know antirez is on HN, so it's strange to say this, but here goes... I always looked up to antirez. Redis was really taking off after I graduated and I was impressed by the whole system and the person behind it. I was impressed to see them walk away to do something different after being so successful. I was impressed to read their blog about tackling difficult problems and how they solved…

I care a lot about programming, but I want to do programming in a way that makes me special compared to machines. When the LLM hits a limit, and I write a function in a way it can't compete, that is good. If I write a very small program that is like a small piece of poetry, this is good human expression. But if I need to develop a feature, and I have a clear design idea, and I can do it in 2 hours instead of 2 weeks, how to justify with myself that just for what I love I use a lot more time? That would be too much of ego, I believe. So even if for me too this is painful, as a transition, I need to adapt. Fortunately I also enjoyed a lot the desing / ideas process, so I can focus on that. And write code myself when needed.

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

#759

Post by antirez »

Thanks for reading / commenting this post. Initially it seemed like I received a bunch of very negative comments, now I read most of the thread, and there are very good points, articulated with sensibility. Thank you.

I wanted to provide some more context that is not part of the blog post. Since somebody may believe I don't enjoy / love the act of writing code.

1. I care a lot about programming, I love creating something from scratch, line by line. But: at this point, I want to do programming in a way that makes me special, compared to machines. When the LLM hits a limit, and I write a function in a way it can't compete, that is good.

2. If I write a very small program that is like a small piece of poetry, this is good human expression. I'll keep doing this as well.

3. But, if I need to develop a feature, and I have a clear design idea, and I can do it in 2 hours instead of 2 weeks, how to justify to myself that, just for what I love, I will use a lot more time? That would be too much of ego-centric POV, I believe.

4. For me too this is painful, as a transition, but I need to adapt. Fortunately I also enjoyed a lot the design / ideas process, so I can focus on that. And write code myself when needed.

5. The reason why I wrote this piece is because I believe there are still a lot of people that are unprepared for the fact we are going to be kinda of obsolete in what defined us, as a profession: the ability to write code. A complicated ability requiring a number of skills at the same time, language skills, algorithms, problem decomposition. Since this is painful, and I believe we are headed in a certain direction, I want to tell the other folks in programming to accept reality. It will be easier, this way.

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

#760

Post by crassus_ed »

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…

Genuine question, doesn't this apply to coding style than actual results? Same applies to writing style. LLMs manage to write great stories but they don't suit my writing style. When generating code it doesn't always suit my coding style but the code it generates functions fine.
Post reply on HN