Agentic Coding Is a Trap • Hacker News Board

Re: Agentic Coding Is a Trap

#161

Post by hibikir » Mon, May 04, 2026, 2:58 AM UTC

cyanydeez wrote: post #11

ex-aws-dude wrote: post #9

The thing is the code quality is still ultimately up to you Nothing stopping you from iterating with the agent till the code is the exact same quality that you yourself would write

Sure, but then it's not really saving you time is it.

In my experience, it sure saves time. a lot of quality has significant mechanical components LLMs do great. Hey, this series of 300 functional tests are reusing the same few patterns without helper methods clarifying intent. Give me an overview of possible meaningful methods that would simplify the duplication. Ok, 2, 4 and 5 are good, but rename 2 to X, and change the order of parameters in 5. Implement across the tests, and make sure it all passes.

Still very significant savings over all that rather mechanical work. It's ultimately cheaper than doing a code review, and it's faster, because there's less need to manage the emotional state of the person whose code is being reviewed. Maybe I am a slow developer or something, but I am getting a lot of quality changes like that done that before I'd not have, solely because of time spent.

And not increasing the quality just causes problems anyway. Given the same quality, more changes mean more outages than before, just by probability. Increasing rate of change demands a similar increase in quality if you don't want your production support costs to go up. So spending at least a bit of time on quality, letting the LLM do the nagging little things that before you didn't do beause they they took too long and were not a core part of quarterly goals is basically mandatory.

Re: Agentic Coding Is a Trap

#162

Post by beej71 » Mon, May 04, 2026, 2:59 AM UTC

zbentley wrote: post #143

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…

I don’t disagree with any of that, but I think the brutal truth is that the priority of most businesses was always that approximate, slipshod, business-driven development. The human engineering process was only coincidentally a check back against the worst outcomes of that philosophy, not intentionally one.

I agree as well. And now they can make slipshod products at 10x speed.

Re: Agentic Coding Is a Trap

#163

Post by wiieee » Mon, May 04, 2026, 2:59 AM UTC

zbentley wrote: post #143

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…

I don’t disagree with any of that, but I think the brutal truth is that the priority of most businesses was always that approximate, slipshod, business-driven development. The human engineering process was only coincidentally a check back against the worst outcomes of that philosophy, not intentionally one.

Yeah but all these firms are going to get destroyed by firms led by people who are more disciplined and enforce rigour in thought etc that’ll be pushed through discouraging over-use of llm’s.

Apple didn’t go from near bankrupt to where it is today without that discipline.

Re: Agentic Coding Is a Trap

#164

Post by BonoboIO » Mon, May 04, 2026, 3:02 AM UTC

20+ years in. For me, agentic coding has been nothing short of a godsend -- not because it writes code for me, but because it lets me explore and prototype things that would have taken days of reading docs and ramping up. The creative surface area of what I can touch in a week has expanded dramatically.

Where I worry is beginners. The hard-won intuition for "this is a reasonable approach" vs. "this will bite you in six months" takes years to develop. With experience, you steer the agent. Without it, the agent steers you -- and it steers confidently in every direction, good and bad alike.

Re: Agentic Coding Is a Trap

#165

Post by orbital-decay » Mon, May 04, 2026, 3:02 AM UTC

bigstrat2003 wrote: post #127

orbital-decay wrote: post #85

>and then pulls the slot machine lever over and over Does anyone really do this? You want verification and self-correction in a loop, not rerolling and cherrypicking. The non-determinism point is really tiresome to hear over and over.

> The non-determinism point is really tiresome to hear over and over. When the problem is fixed, you'll stop hearing about it.

That's the question, how is it even a problem? There's nothing to fix. Don't reroll, verify and fix if incorrect. Repeat until it's right.

Re: Agentic Coding Is a Trap

#166

Post by komali2 » Mon, May 04, 2026, 3:03 AM UTC

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…

> We're in a cesspit of business driven development

In a business-driven world with business-driven governments writing business-driven rules, what's the alternative if you want to optimize for success?

Re: Agentic Coding Is a Trap

#167

Post by FridgeSeal » Mon, May 04, 2026, 3:04 AM UTC

danenania wrote: post #152

byzantinegene wrote: post #116

Earlier quoted context omitted.

you have 35 years of experience and have already built up the learning capability and general framework to acquire new knowledge. you know how to use agentic coding as a tool to supplement your work. the juniors who start today don't have that, they overrely on agentic coding and do not know what they don't know

If a junior builds something with agents that turns into a mess they can’t debug, that will teach them something. If they care about getting better, they will learn to understand why that happened and how to avoid it next time. It’s not all that different than writing code directly and having it turn into a mess they can’t debug—something we all did when we were learning to program. It is in many ways far easier to w…

> that will teach them something. If they care about getting better,

This pre-supposes the idea that the business is _willing_ to let that happen, which is increasingly unlikely. The current, widespread attitude amongst stakeholders is “who cares, get the model to fix it and move on”.

At least, when we wrote code by hand, needing to fix things by hand was a forcing function: one that now, from the business perspective, no longer exists.

Re: Agentic Coding Is a Trap

#168

Post by ryandrake » Mon, May 04, 2026, 3:07 AM UTC

CodeShmode wrote: post #123

ryandrake wrote: post #100

Using AI to go faster is optimizing the wrong thing. At every place I've worked, the "code writing" part takes the least amount of time, compared to all the other things you need to do in order to implement a feature. Let's examine a feature that takes a day to code: First, you've got to plan everything, using whatever Agile or Waterfall planning ritual your company uses, get the task breakdown, file the JIRA tickets…

Or you can have a conversation with an agent to build up a requirements/plan spec, asking it to analyse existing code patterns. When it seems like the agent has a good understanding of what needs to be done and how. Ask it to implement, keeping changes as a local spike. Ask the agent questions about all the other teams' code, reaching out to them for questions it can't answer or clarification. With agent capabilities…

I have no idea what a “spike” is, but this seems like a good way to build software when there are no consequences to getting it wrong.

What happens if this “spike” violates someone’s patent or puts the company at legal/regulatory risk? What if it leaks users’ personal information? What if it introduces a vulnerability that my 13 year old can exploit? What if it crashes 2 million of your users’ devices because it didn’t anticipate some unusual configuration? What if the code totally conflicts with some other team’s future plans and you didn’t know because they never reviewed it?

This kind of yolo “just try it” development only works if you are very small and low-profile, don’t have hundreds of millions of users, or your software is inconsequential (nobody cares if it goes down or doesn’t work).

Re: Agentic Coding Is a Trap

#169

Post by jfreds » Mon, May 04, 2026, 3:08 AM UTC

SpicyLemonZest wrote: post #148

ookblah wrote: post #122

Earlier quoted context omitted.

someone probably made this same argument against certain frameworks over the years and juniors still figured it out. we need to stop trying to babysit learning for hypothetical situations. the bar to "start" is lower and the bar to actually competency is higher now, juniors who want to actually learn instead of just pressing enter over and over again will do so regardless of whatever you do to "help" them.

It's not really a hypothetical. I work with one junior who's submitted an incorrect bugfix 3 times and counting; he seems genuinely incapable of processing the idea that there's a correctness issue he has to resolve, rather than a prompt engineering issue that will allow Claude to figure it out if only he asks in the right way.

To be fair this was a thing before AI as well…

Re: Agentic Coding Is a Trap

#170

Post by hibikir » Mon, May 04, 2026, 3:08 AM UTC

everyone wrote: post #72

Im seeing the word "agentic" a lot here. Is there a difference between "Agentic Coding" and "I put prompt into gpt or claude and pasted code into my file" ?

It reads your other code so it can match the style, it runs the compiler, if any, it runs the tests, and if anything fails through any of it, it handles the errors and works on it.

If you ask it to, say, update the major version of some library, it will read the source of the new version, check the deprecations, attempt the changes based on that, rerun tests... a completely different level of utility.

It's even more ridiculous with access to server logs and such, as you can point it to a chart, say there were some errors in X service at Y time, and it'll dutifully look at logs in that window, check traces if available, look at caller services, check the database if needed, and come up with a hypothesis on what happened based on all the available information. It might miss things, but that's why you are there too. No need to be a prompting wizard that gives it everything it needs to get you the right answer in one shot: It's like pair programming with someone that has encyclopedic knowledge in many topics, but hasn't worked at your company before. A completely different experience.