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

Codegen is not productivity

antifound.com

Post reply on HN
Print view View original

31–40 of 103 posts

Re: Codegen is not productivity

#31

Post by emp17344 »

hibikir wrote: post #25
emp17344 wrote: post #4

The collaboration aspect is what many AI enthusiasts miss. As humans, our success is dependent on our ability to collaborate with others. You may believe that AI could replace many individual software engineers, but if it does so at the expense of harming collaboration, it’s a massive loss. AI tools are simply not good at collaborating. When you add many humans to a project, the result becomes greater than the sum of…

I look at it backwards: A few humans improves a project. But once you get to sufficient sizes, principal-agent problems dominate. What is good for a division and what is good for the company disagree. What is good for a developer that needs a big project for their promotion package is not what the company needs. A company with a headcount of 700 is more limber and better aligned than when it's 3,000 or 30,000. It's a…

Yes, which is why every successful company has exactly 4 people and no more. Collaboration goes beyond your immediate team members - if you work for an organization, you’re supported by it in ways you may take for granted. Replace this structure with AI models, and the whole thing would fall apart.

Re: Codegen is not productivity

#32

Post by felipellrocha »

jwilliams wrote: post #21

> Humans and LLMs both share a fundamental limitation. Humans have a working memory, and LLMs have a context limit. But there’s a more important difference: I can’t spin up 20 decent human programmers from my terminal. The argument that "code was never the bottleneck" is genuinely appealing, but it hasn’t matched my experience at all. I’m getting through dramatically more work now. This is true for my colleagues too.…

I guess that what people debate on here is what “decent” mean. From my experience, these llms spit out dog shit code, so 20 agents equal 20x more dog shit.

Re: Codegen is not productivity

#33

Post by jwpapi »

I have to be honest. I’ve written a lot of pro-ai / dark-software articles and I think Im due an update, cause it worked great, till it didn’t.

I could write a lot about what I’ve tried and learnt, but so far this article is a very based view and matches my experience.

I definitely suffered under the unnecessary complexity and wished to never’ve used AI at moments and even with OPUS 4.6 I could feel how it was confused and couldn’t understand business objectives really. It became way faster to jump in code, clean it up and fix it myself. I’m not sure yet where and how the line is and where it will be.

Re: Codegen is not productivity

#34

Post by christophilus »

Frieren wrote: post #22
some_random wrote: post #3

You can write cope like this all you want but it doesn't change the fact I can ship a feature in few days that previously would have taken me a few weeks.

> I can You can because, I guess, your project may have a small scope, few people working on it, no dependencies etc. I cannot, because each line that I change has an effect in millions of other lines and hundreds of other people, and millions of users. Different situation, different needs.

> each line that I change has an effect in millions of other lines

That sounds like an architectural problem.

Re: Codegen is not productivity

#35

Post by dolebirchwood »

emp17344 wrote: post #4

The collaboration aspect is what many AI enthusiasts miss. As humans, our success is dependent on our ability to collaborate with others. You may believe that AI could replace many individual software engineers, but if it does so at the expense of harming collaboration, it’s a massive loss. AI tools are simply not good at collaborating. When you add many humans to a project, the result becomes greater than the sum of…

> When you add many humans to a project, the result becomes greater than the sum of its parts. When you add many AI tools to a project, it quickly becomes a muddled mess.

I have absolutely been on projects where there were too many cooks in the kitchen, and adding more people to the team only led to additional chaos, confusion, and complexity. Ever been in a meeting where a designer, head of marketing, and the CTO are all giving feedback on what size font a button should be? I certainly have, and it's absurd.

One of my worst experiences arose due to having a completely incompetent PM. Absolutely no technical knowledge; couldn't even figure out how to copy and paste a URL if his life depended on it. He eventually had to be be removed from a major project I was on, and I was asked to take over PM duties, while also doing my dev work. I was actually happy to do so, because I was already having to spend hours babysitting him; now I could just get the same tasks done without the political BS.

Could adding many AI tools to a project become problematic? Maybe. But let's not pretend throwing more humans at a project is going to lead to some synergistic promised land.

Re: Codegen is not productivity

#36

Post by zer00eyz »

I went to look at some of the authors other posts and found this:

https://www.antifound.com/posts/advent-of-code-2022/

So much of our industry has spent the last two decades honing itself into a temple built around the idea of "leet code". From the interview to things like advent of code.

Solving brain teasers, knowing your algorithms cold in an interview was always a terrible idea. And the sort of engineers it invited to the table the kinds of thinking it propagated were bad for our industry as a whole.

LLM's make this sort of knowledge, moot.

The complaints about LLM's that lack any information about the domains being worked in, the means of integration (deep in your IDE vs cut and paste into vim) and what your asking it to do (in a very literal sense) are the critical factors that remain "un aired" in these sorts of laments.

It's just hubris. The question not being asked is "Why are you getting better results than me, am I doing something wrong?"

Re: Codegen is not productivity

#37

Post by ericmcer »

agent5ravi wrote: post #19

[flagged]

It would be interesting seeing how good LLMs are at interactive system design type work. I find them to be way too positive when I need them to shut me down or redirect my ideas entirely.

We need a comparison between an LLM and an experienced engineer reviewing a juniors system design for some problem. I imagine the LLM will be way too enthusiastic about whatever design is presented and will help force poor designs into working shape.

Re: Codegen is not productivity

#38

Post by nubg »

rules of thumb for when to take blog posts about AI coding seriously:

- must be using the latest state of the art model from the big US labs

- must be on a three digit USD per month plan

- must be using the latest version of a full major harness like codex, opencode, pi

- agent must have access to linting, compilation tools and IDE feedback

- user must instruct agent to use test driven development and write tests for everything and only consider something done if tests pass

- user must give agent access to relevant documentation, ie by cloning relevant repositories etc

- user must use plan mode and iterate until happy before handing off to agent

- (list is growing every month)

---

if the author of a blog post about AI coding doesnt respect all of these, reading his blog posts is a waste of time because he doesn't follow best practices

Re: Codegen is not productivity

#39

Post by jwpapi »

There is a saying you need to write an essay 3 times. The first time its puked out, the second is decent and the third is good.

It’s quite similar with code, and with code less is more. for try 1 and 2

Post reply on HN