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

Agentic Coding Is a Trap

larsfaye.com

Post reply on HN
Print view View original

331–340 of 403 posts

Re: Agentic Coding Is a Trap

#331

Post by larsfaye »

monksy wrote: post #20

I kind of think this article misses the mark a little. There is skill loss from heavy AI use. But I want to acknowledge the awkward elephant in the room. AI Is making people too fast. I don't mean that a faster output is bad. It's a faster output and code rather than a full understanding and experience in producing the code. It's rewarding people who try to talk about business value rather than the people that are bu…

Author of the article here (had no idea someone shared it! Just found out through analytics).

I actually mention this exact thing it the article under the section "LLMs accelerate the wrong parts", which seems to be saying exactly what you're saying:

https://larsfaye.com/articles/agentic-coding-is-a-trap#llms-...

I would find it hard to believe there is any developer in history ever uttered the words:

"I really wish I had a tool that could generate code I don't understand, and at a rate faster than I can review".

Re: Agentic Coding Is a Trap

#332

Post by habinero »

helloplanets wrote: post #274
habinero wrote: post #264

Earlier quoted context omitted.

No, it's the same for math from what I've seen, aka it can do some of the easy things, usually with a lot of help. People usually mean the Erdos problems (aka "a list of things Paul Erdos thought were neat") and, well, here: > While Erdős generated a huge number of problems, they are not all equally significant and important. I have, unfortunately, seen some mathematicians grow dismissive of Erdős problems recently,…

You're right, definitely as a helper, not a one shot thing. Here's an example unrelated to the Erdos problems: https://arxiv.org/abs/2510.23513

I flat out don't take arxiv papers seriously without a lot of corroboration. Basically ~anyone can post ~anything to it. They do spam moderation but no content review.

Also that paper admits the problem turned out to be pretty trivial and was only unsolved because nobody had bothered to try that hard (page 11)

There's a lot of problems with paid scientific journals being a walled garden and I am by no means defending that system, buuuut it's also true that anything published to an open repository is almost certainly there because it wasn't good enough for anything else.

Re: Agentic Coding Is a Trap

#333

Post by threethirtytwo »

rimliu wrote: post #326
threethirtytwo wrote: post #292

Earlier quoted context omitted.

Self driving is not around the corner. I sit in the back seat of an AI driven car on a daily basis. There is no living being sitting on the front seat and that car goes on the freeway. This is a regular and very common thing where I live:

Powered by chaps in Phillipinnes. Your "regular and very common" thing is close to calling railoroads self-driving.

You’re kinda delusional. It’s here and people use it and you’re still moving the goal posts.

For geniuses like you it will still be around the corner only until you can call a Waymo in the middle of the fucking ocean. You’re right. It will never happen.

Re: Agentic Coding Is a Trap

#334

Post by bhagyeshsp »

lelanthran wrote: post #289
bhagyeshsp wrote: post #159

Earlier quoted context omitted.

Self-taught, "junior" here. Due to English-language limitation my most adult life, I struggled to code. Used visual coding etc. But of course, I can't make a living on drag-and-drop harness. Comes in GPT-3.5, accelerated my learning. Now I'm running my incorporated company, just launched one software-hardware hybrid product. Second one is a micro-SaaS in closed beta. The point is: when people use "juniors" as a fixed…

> I struggled to code > ... > Comes in GPT-3.5, accelerated my learning. So now you can code? If I sat you in front of a computer with no internet and no GPU but your choice of IDE, you would actually be able to produce a product?

Okay, after re-reading the thread, looks like, this question was not in bad faith. While commenting, I was reading from bottom-to-top and so made an opinion about you based on your bottom thread comments (which still stands correct), but for other readers, they deserve an answer, not the questioner.

Anyone wondering about my proficiency, I can code without internet or AI help. But it takes enormous amount of time and mistakes.

Re: Agentic Coding Is a Trap

#335

Post by djmips »

solenoid0937 wrote: post #95
ryandrake wrote: post #86

Earlier quoted context omitted.

What kind of place do you work where you get dragged into a meeting halfway through and then are peppered with technical questions without context, that you're expected to answer on the spot? Please let us know because I'm sure a lot of us want to avoid such a place. "I'll need to study the docs and code to answer these questions properly" is a perfectly fine (and very diplomatic) response to treatment like that.

This can happen more or less anywhere if you spend enough time at a company. At some point you'll get pulled into a meeting like this because others think you're in expert in a codebase/area you're not.

Like if your the manager of a group and you do little code writing.

Re: Agentic Coding Is a Trap

#337

Post by djmips »

WorldMaker wrote: post #180
lgrapenthin wrote: post #144

Earlier quoted context omitted.

Indeed. Generated code is also harder to read because it violates all semantic expectations that rely on the mental model of a human author. A generated piece of code is linguistically plausible but often unknowingly imitates common idioms so incoherently that the actual bug may be accidentally disguised in a way no sane human (even a bad programmer) could have come up with. Since LLMs have no internal evaluation, as…

I tried to capture some of my feelings on this on a recent personal blog post/rant. The easiest phrase is that LLMs are "legacy code as a service". They are trained on other people's legacy code. (No one is intentionally feeding LLMs their best proprietary code.) They produce output that is "Day 1 Legacy Code" in the sense that there's no human code owner to take responsibility and you might be able to ask the LLM th…

"legacy code as a service" - that's apt. But would they be better if they trained exclusively on 'good code'? I know I don't know the answer to that question and I get the feeling that few people actually understand how they work enough to feel comfortable with asserting that to be true.

Re: Agentic Coding Is a Trap

#338

Post by larsfaye »

phendrenad2 wrote: post #102

> This is the sentiment being hyped up around the industry currently: traditional coding is all but dead, and Spec Driven Development (SDD) is the future. You generate a plan, and disconnect from writing any code Agentic agile > agentic waterfall (at least for now) Don't give the AI a spec, work with it every step of the way. > pulls the slot machine lever over and over (link to "One More Prompt: The Dopamine Trap of…

Author here....

"An increase in the complexity of the surrounding systems to mitigate the increased ambiguity of AI's non-determinism"

I'm referring to the layers of review that are needed to be put in place to reign in the fact that the code that is generated is blurry and obfuscated, and in amounts that exceed what someone can review in one or two sittings. I'm seeing multi-phase AI review stages that will try and distill review finer each time. Then another agent layer to document. Then another to create a PR. Then the human reviews, but uses Coderabbit locally. Then sends it back into the pipeline and round and round we go, all because there's simply too much volume of code to review.

Re: Agentic Coding Is a Trap

#339

Post by WorldMaker »

dilyevsky wrote: post #214
WorldMaker wrote: post #184

Earlier quoted context omitted.

Respectfully, the current models are all trained on everyone else's legacy code as of roughly six months ago and largely always will be. If I'm doing my job right an LLM cannot meet my personal quality bar on its own because I will always need innovation and excellence they will never see and thus cannot deliver. I also think that training these tools on my personal quality bar is more work than just writing it mysel…

High quality c++ code today looks exactly same as it did six months, hell, six years ago. Innovation doesn’t come from code tricks

True innovation is doing something new that has never been seen before. Even if you are doing it in a stable language that's just a stable poetry form (rhyme and meter and formatting), the real magic is the content of the poetry, and the real beauty of code is when the poetry reads well to both audiences, the compiler and the next maintainer, on multiple levels, the literal and the metaphorical.

LLMs can't reach the metaphorical. LLMs don't know what true beauty is. I will grant you they have gotten great at the literal and the poetry forms. But it is the beauty that elevates things to my quality bar, and makes a difference between "legacy code" and "innovation" to me.

Re: Agentic Coding Is a Trap

#340

Post by djmips »

larsfaye wrote: post #331
monksy wrote: post #20

I kind of think this article misses the mark a little. There is skill loss from heavy AI use. But I want to acknowledge the awkward elephant in the room. AI Is making people too fast. I don't mean that a faster output is bad. It's a faster output and code rather than a full understanding and experience in producing the code. It's rewarding people who try to talk about business value rather than the people that are bu…

Author of the article here (had no idea someone shared it! Just found out through analytics). I actually mention this exact thing it the article under the section "LLMs accelerate the wrong parts", which seems to be saying exactly what you're saying: https://larsfaye.com/articles/agentic-coding-is-a-trap#llms-... I would find it hard to believe there is any developer in history ever uttered the words: "I really wish…

I know what that feels like having been a manager of a team of coders who were generating code faster than I could fully understand and review. I imagine how much worse that would be with Agentic coders.
Post reply on HN