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

261–270 of 403 posts

Re: Agentic Coding Is a Trap

#261

Post by noobermin »

These blogposts (no doubt written with the help of AI) have been the topic of many a comment here and elsewhere across the internet for years now. The atrophying of skills is a serious concern and has been voiced again and again since 2022 by everyone skeptical of AI and I just think some people and some places just don't care.

At some point, if you're just pulling the lever on the slop machine with zero insights into your code, may be your boss is justified in asking why you should earn more than 50k a year.

Re: Agentic Coding Is a Trap

#262

Post by nyssos »

dilyevsky wrote: post #235
nyssos wrote: post #220

Earlier quoted context omitted.

You're presuming too much about what OP's quality standards are. Can SOTA models outperform the average junior engineer? Yes, obviously. Can they match the best human engineers, if those humans were given all the time and interest in the world? Equally obviously not. I use hundreds of millions of tokens a month, and LLMs have completely transformed the way I work. They're also, frankly, pretty mid programmers.

most people are around mid by definition. mid is good. a lot of companies pay good money to find mid devs.

Yes, and? Something can be both scare and inadequate to a given task. FAANG L5s cost a pretty penny but I wouldn't trust a random one to prove a crypto library correct.

Re: Agentic Coding Is a Trap

#263

Post by andrekandre »

notepad0x90 wrote: post #201
andrekandre wrote: post #98

Earlier quoted context omitted.

> standardized like AGILE and SCRUM perhaps too cynical, but if its anything like agile and scrum in $CORPORATION it will just add to the daily slog and gum up everything...

That's exactly what I predict as well, I think it's inevitable. there will be middle managers and project managers needing a stick with which to beat the LLM mess into order, and keep themselves relevant, and it will suck all the same. But even such efforts result in establishment of good practices. In attempting to discredit the "slog" devs will establish "but instead, we should be doing $X".

i would hope so, as long as "good practices" really are good (for what thats worth anyway).

again, maybe overly cynical but ime "good practices" usually end up getting warped into "bad practices" caused by cargo-culting/up-selling by consultants as they try to mass-produce a new dev paradigm

Re: Agentic Coding Is a Trap

#264

Post by habinero »

helloplanets wrote: post #212
mikert89 wrote: post #22

I've come to the conclusion that if AI can do it, its not hard. None of the complicated software i work on can be reliably written by ai yet

SotA models have cracked a handful of research-level math problems though. The default Claude Code style harness is bad for complicated problems as well. Just taking the specific class or function you're working on, and putting it into a deep research style loop yields way better results. Limiting the initial context by hand is still the way to go in a lot of cases.

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, perhaps because they have seen reports of AI solving problems on this site that turned out to be quite simple, and wrongly generalised this to assume that all problems posed by Erdős are amusing novelties, of the level of olympiad problems.

From: https://www.erdosproblems.com/forum/thread/blog:5

The rest of the article isn't about AI at all, but I did think it was funny that it describes mathematicians as having more or the same opinion as SWEs.

Re: Agentic Coding Is a Trap

#265

Post by cernocky »

hibikir wrote: post #151
CGamesPlay wrote: post #135

Earlier quoted context omitted.

Exactly this. We need to be more precise than blanket statements like "agentic coding is a trap" and start figuring out what a "tasteful" application of agentic coding looks like. ChatGPT is destroying liberal arts curriculums because students can choose to not do anything of the thinking themselves and produce mediocre work that passes the bar. I think the same problem is showing itself with agentic coding, just wit…

On liberal arts is simply a matter of what the students want to get out of the class, vs what the teacher wants the students to do: There's a huge disconnect in goals and expectations, so there's no way for the teacher to actually win. The fact that there's such disconnect should give the departments pause. This doesn't happen at all for using agentic coding: What the programmer wants and what the boss wants are pret…

> what the students want to get out of the class, vs what the teacher wants the students to do: There's a huge disconnect in goals and expectations, so there's no way for the teacher to actually win. The fact that there's such disconnect should give the departments pause.

Unless the teacher's role is to scaffold and support the students in acquiring what the students want, gain trust and lower the disconnect.

Re: Agentic Coding Is a Trap

#266

Post by habinero »

slopinthebag wrote: post #82
mikert89 wrote: post #22

I've come to the conclusion that if AI can do it, its not hard. None of the complicated software i work on can be reliably written by ai yet

Yeah this is the same conclusion I have. I primarily use AI for UI code, and guess what, it's all basically mechanical drudgery anyways. Put a div here, or put a Box here, apply some style rules, etc. This shit should have been automated decades ago yet for some reason we're still writing the same stuff with a different "twist" today. Now if your career is built on writing out the same boilerplate code in its infinit…

I had AI fuck up writing a scraper[0]. A scraper. It hit a snag with cookies and spiraled into a tizzy. I liked the part where it assured me it could resume from the point of failure, while starting over for the 10th time because it had written no such code lol

[0] For those with AI scraping PTSD, it was a government site with public domain info and I know how to scrape politely

Re: Agentic Coding Is a Trap

#267

Post by Rekindle8090 »

fnordpiglet wrote: post #51

Interestingly I’ve learned more about languages and systems and tools I use in the last few years working with agentic coding than I did in 35 years of artisanal programming. I am still vastly superior at making decisions about systems and techniques and approaches than the agentic tools, but they are like a really really well read intern who knows a great deal of detail about errata but have very little experience.…

[dead]

Re: Agentic Coding Is a Trap

#268

Post by habinero »

fathermarz wrote: post #60

The slot machine lever is my least favourite opinion on the subject. Also, let’s not forget. The developer is rarely the person pitching the feature, and is normally given the constraints and the PRD… Soooo people can keep tiptapping on the keyboard, but eventually they need to open their mind to the possibility that “the old way” is actually dead.

> The developer is rarely the person pitching the feature, and is normally given the constraints and the PRD

This heavily depends on the industry and company culture.

I've pitched plenty of features and I've basically never had a spec land on my desk ready to go. Part of my job as a SWE is to help product folks decide what to build.

Re: Agentic Coding Is a Trap

#269

Post by habinero »

iandanforth wrote: post #111

Try this thought experiment. If, in 6 months, the agents were better coders than you are, would this argument still hold? This is a personal thought experiment so think it through for yourself. What would the consequence be if the agents really were better than you and you acknowledged that? The major premise of "It's a trap!" is that it matters if you lose your coding skill. (I'll gloss over general critical thinkin…

Thanks, I collect data breaches and this post reminded me to set up pricing alerts for more drives to expand the NAS.

Re: Agentic Coding Is a Trap

#270

Post by docheinestages »

AI is just another tool and a new layer of abstraction. Do you really think the majority of people who write in high level languages truly understand what's going on under the hood? Do they really? Or is there at some point a divide between what needs to be done, how the application or logic should perform, and the actual translation of all that into machine code?
Post reply on HN