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

The Tower Keeps Rising

lucumr.pocoo.org

Post reply on HN
Print view View original

201–210 of 280 posts

Re: The Tower Keeps Rising

#201

Post by slopinthebag »

gwbas1c wrote: post #26
snarf21 wrote: post #16

Earlier quoted context omitted.

It feels to me like I'm stuck doing code reviews for a junior dev all day so I use it as little as possible and mostly to look for things I may have missed.

It's great for "mechanical" changes. For example, yesterday I came across some unit tests that didn't have error messages in their assertions. Normally, it takes me ~10 minutes to fix a handful of tests in this situation. In this case, I gave a 2-3 sentence prompt, went to the bathroom, and reviewed the result after I washed my hands. Saved me a bunch of time! I encourage you to accept a feeling of "imposter syndrome…

Yes it's so useful for mechanical changes, refactors, and creating similar but slightly different components etc. It turns out that when you feed the word prediction machine a bunch of examples of what you want, and then some text that it can use to predict more text, it can do a good job!

The hard part is what text you feed it and how to judge the output.

Re: The Tower Keeps Rising

#203

Post by moffkalast »

zemo wrote: post #35

Anakin: "a developer with an agent will be dramatically more capable of changing a codebase" Padmé: "For the better, right?" Anakin: (gazes in silence) Padmé: "For the better, right?"

Not to worry, we're still flying half a project.

Re: The Tower Keeps Rising

#204

Post by Cthulhu_ »

zemo wrote: post #35

Anakin: "a developer with an agent will be dramatically more capable of changing a codebase" Padmé: "For the better, right?" Anakin: (gazes in silence) Padmé: "For the better, right?"

A fallacy that a lot of people have is that productivity equals progress. Programmers (and their managers) using LOC as a target metric, writers using words/chapters written, etc. For some reason this fallacy is reinvented and repeated every so often.

Re: The Tower Keeps Rising

#205

Post by Cthulhu_ »

jeffreyrogers wrote: post #7

My comment is not directly responding to the essay, but it got me thinking about about how agentic programming is much more akin to management than it is to actual programming. Managers generally only have a high level idea of what ICs are working on and often don't have the time, bandwidth, and in some cases ability to understand everything the ICs they're supervising are doing. As more and more software gets writte…

While this is true to a point, the other factor is that developers are hired and tested for having certain skills and specializations. While I'm sure LLMs can be good at things, the question is whether their manager can accurately judge the output. I suppose this problem applies to developers too, but developers have peers and processes.

So as someone managing LLMs you need to put those processes in place too. The risk is that one tries to do too much and loses overview / insight. Focusing on getting the tower tall instead of sturdy, if you will.

Re: The Tower Keeps Rising

#206

Post by Cthulhu_ »

prymitive wrote: post #2

It used to be that you need a good reason to make huge refactorings, because it’s often so much work. Now agent can rewrite half of your code if your prompt is vague enough and you don’t actual try to review it all. And so the “soul” of a program can change dramatically every single day. It’s both great and very much not so.

If the "soul" of a program (which is a vague term but I think I get what you mean) changes daily, that's indicative of a lot of churn, and a lot of churn is not a good idea in any project.

it's like changing how the tower of babel should be built daily. Just because you can doesn't mean you should.

Re: The Tower Keeps Rising

#207

Post by slopinthebag »

jdw64 wrote: post #76

Since GPT 5.2, AI has been writing code much better than I can. In 5.6, it beat Tourlist in competitive coding. After seeing that, I only practice about an hour a day just to keep the feel of coding. Honestly, rather than pointless debates about whether human coding is bad or AI coding is bad, I just think it's good to build tools that help me understand the world. I don't really care whether it's hand-coded or bad c…

For a lot of people, LLM's are actually doing a better job than what they are capable of. I do worry that they are the people first up for replacement, since they don't really provide much value that the LLM itself can't provide. There isn't much point in paying a human to prompt an LLM if you could do it yourself, the value is in someone with the skill and judgement to both prompt it correctly and validate the output - and if the LLM is producing better code than the human is capable of they clearly don't have any of that.

Personally I really like using LLMs because they have made certain things a lot more productive, but I don't feel like my job has really changed at all. I have a new way of generating code, but my value has never been my (abysmal) typing speed or knowledge of algorithms or how fast I can centre a div. It's been in the stuff that LLMs still haven't pierced, and probably never will.

Re: The Tower Keeps Rising

#208

Post by hahahaa »

arkmm wrote: post #109
tekacs wrote: post #6

I've said for a long time that composability in software is a bit like playing Tetris: the lines have to clear. I feel like that gives an even more literal tower-rising metaphor, and that's what it feels like people using agents naively (and software engineers of lower skill or earlier-career), end up violating. Agents are getting better at folding things into themselves, especially if you direct them to... but unfor…

I think part of the problem is the context windows for humans are actually much smaller than what an LLM can keep track of today. The small context window of humans is a feature that forces modularity and abstraction in software engineering so that you can decompose what you're working on into something that can fit into your head. But since LLMs can fit so much more in their head, so to speak, they don't have this s…

Also a human has to explain the code. There is a social contract and producing slop gets you fired. Especially as you produce it much slower than an LLM.

Re: The Tower Keeps Rising

#209

Post by hahahaa »

sph wrote: post #188
tekacs wrote: post #6

I've said for a long time that composability in software is a bit like playing Tetris: the lines have to clear. I feel like that gives an even more literal tower-rising metaphor, and that's what it feels like people using agents naively (and software engineers of lower skill or earlier-career), end up violating. Agents are getting better at folding things into themselves, especially if you direct them to... but unfor…

> I've said for a long time that composability in software is a bit like playing Tetris: the lines have to clear. Great metaphor. When I hear people claim 20x productivity with AI assistance, I imagine a Tetris game where pieces fall 20x faster. As you say, those lines still have to clear.

Yeah I would love to sit down and see what exactly one of the 20x people us doing. Either I spot the flaw (99%) or there is some utter magic they are doing (1%) which I could try to learn.

Re: The Tower Keeps Rising

#210

Post by peter_retief »

It is a great analogy.

Also quite like Linus Torvalds likening of AI to a compiler.

He argues that calling AI the "author" of code is the equivalent of saying a compiler wrote your code.

He views AI as an incredibly powerful productivity layer, much like the historic progression from machine code to assemblers, and then to higher-level compilers!

Post reply on HN