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

361–370 of 403 posts

Re: Agentic Coding Is a Trap

#361

Post by bulbar »

throwaway041207 wrote: post #224
bulbar wrote: post #217

Earlier quoted context omitted.

This assumes failures can be detected and fixed more easily than generating the corresponding change. I am not convinced that's the case. Counter points to my own arguments: 1. We don't know yet in detail what AI is good at. 2. AI doesn't need to be perfect, just "good enough", whatever that means for a specific project. More failures while saving hundreds of thousands dollars each year might be acceptable, for examp…

> 2. AI doesn't need to be perfect, just "good enough", whatever that means for a specific project. More failures while saving hundreds of thousands dollars each year might be acceptable, for example. This I think is the unexplored aspect of what's happening right now. Guardrails around "good enough" systems is where the future value lies. In the future code will never be as good as when the artisans were writing it,…

Validating / Verifying mediocre code is pretty hard as nobody was able to agree what that even means.

Re: Agentic Coding Is a Trap

#362

Post by bulbar »

throwaway041207 wrote: post #215
bulbar wrote: post #198

Earlier quoted context omitted.

Just as "use code for contracts" failed for crypto currencies, "use AI output as prod" will fail for AI. Both is based on "just don't make catastrophic mistakes anymore". You also wrongly assume that requirements can always easily expressed as natural language. Another point: Software Engineering always starts where tooling capabilities stop. You don't get a competitive advantage by building without engineers what an…

> Another point: Software Engineering always starts where tooling capabilities stop. You don't get a competitive advantage by building without engineers what anybody everybody else can build without engineers. I'd note here that the long arc of software engineering has been commodifying the discipline into tooling. Ask any unix greybeard how shitty modern abstractions are and they'll give you all you can stomach and…

Well, ask any engineer about any code... ;-).

Re: Agentic Coding Is a Trap

#363

Post by gitaarik »

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" ?

Is coding without the "agentic" part any different from copy pasting code from the internet like a script kiddy?

Re: Agentic Coding Is a Trap

#364

Post by anon-3988 »

danenania wrote: post #358
anon-3988 wrote: post #356

Earlier quoted context omitted.

Don't you see the problem? Now engineers literally do not have any leverage. Did the model make it work? Yes? Then ship it, what are we waiting around for?

That sounds pretty much the same as it’s always been? It used to be: “Does the happy path work? Then ship it! There’s no time to make it robust or clean up tech debt.” Now there actually is time to make things robust if you learn how to do it.

> Now there actually is time to make things robust if you learn how to do it.

What makes you think you are going to be given time to polish it? You would be pushed to another project. You have more responsibilities with none of the growth.

Re: Agentic Coding Is a Trap

#365

Post by lelanthran »

munksbeer wrote: post #348
lelanthran wrote: post #322

Earlier quoted context omitted.

> I don't know what industry you work in or what developers surround you, Why would that matter? I'm not giving you my experience of developers next to me, I'm telling you what I gleaned from published reports.

I don't believe those figures. Perhaps we could discuss more if you linked the reports. In any case, I know how these arguments go. It doesn't really matter.

> I don't believe those figures. Perhaps we could discuss more if you linked the reports.

No report is going to help because there are no actual figures for token providers at the moment. We'll have to wait for them to IPO before we'll know for sure.

Re: Agentic Coding Is a Trap

#366

Post by danenania »

anon-3988 wrote: post #364
danenania wrote: post #358

Earlier quoted context omitted.

That sounds pretty much the same as it’s always been? It used to be: “Does the happy path work? Then ship it! There’s no time to make it robust or clean up tech debt.” Now there actually is time to make things robust if you learn how to do it.

> Now there actually is time to make things robust if you learn how to do it. What makes you think you are going to be given time to polish it? You would be pushed to another project. You have more responsibilities with none of the growth.

It takes very little time to polish now.

Re: Agentic Coding Is a Trap

#367

Post by larsfaye »

jmuguy wrote: post #53
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.…

This post does not make the claim that "you should know everything about everything you work on" - its making the claim that writing code and being able to read code effectively are intrinsically linked.

Author here. Thank you. I absolutely was not stating that, and I don't think its possible or necessary to "know everything", but there's certainly a movement in the industry (and not a small one) that is advocating to abandon even looking at code. It started with Karpathy's "vibe coding" tweet and has extended to now where entire teams are performing "LGTM" level code reviews, while simultaneously reporting that they are finding it difficult to remember how to read, nevertheless write, code properly. "Thinking in code" is a form of thinking that is distinctly different than staying at the higher engineering levels of planning and architecture, and yet they are completely intertwined and interdependent. I plan better when I am engaging with code, and I code better when I know how to plan properly.

Re: Agentic Coding Is a Trap

#368

Post by larsfaye »

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.…

> The claim you should know everything about everything you work on is an intensely naive one.

Author here. Where did you find I was stating that? As other users said, that's not at all found in my writing. The rest of your post goes on a tangent about this notion, but seems like its more of a personal pontification, rather than a critique of anything I wrote.

Re: Agentic Coding Is a Trap

#369

Post by larsfaye »

thedevilslawyer wrote: post #226
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…

LLMs are plenty innovative and generate good quality code by default, and great quality code when directed well. If you're not seeing this, at best you're probably unable to direct them or use them well. FWIW, if you don't believe the above, I challenge you to put up a quick git repo, where you are unable to get the deserved quality out, and we can quickly show you how the same quality is available via SOTA agents, w…

I do agree with this. I was able to get exactly what I needed even out of GPT3.5. If you put enough parameters and examples, along with a real solid system prompt and (if you can) proper temperature and topK/topP, there's no reason they can't basically function like "smart typing assistants". The issue is that its a sliding scale of ambiguity to chaos. The more ambiguity, the more the LLM fills that in. And it can be very difficult and time consuming to know when you're being ambiguous or not (you don't know what you don't know, OR, you can't track what you aren't tracking).

Depending on the task, it can sometimes be just as arduous to produce enough guidance and guardrails to get the LLM to output exactly what you need that you can trust without issue or extensive review than it is to write it yourself and use the LLM just for ad-hoc generation. It's a constant balance and an endless amount of micro-decisions, honestly, but it's pretty essential to stay engaged and not YOLO with agents the way so many are. Most of my interactions with models these days are done in pseudo-code.

Re: Agentic Coding Is a Trap

#370

Post by jmuguy »

larsfaye wrote: post #367
jmuguy wrote: post #53

Earlier quoted context omitted.

This post does not make the claim that "you should know everything about everything you work on" - its making the claim that writing code and being able to read code effectively are intrinsically linked.

Author here. Thank you. I absolutely was not stating that, and I don't think its possible or necessary to "know everything", but there's certainly a movement in the industry (and not a small one) that is advocating to abandon even looking at code. It started with Karpathy's "vibe coding" tweet and has extended to now where entire teams are performing "LGTM" level code reviews, while simultaneously reporting that they…

I've been thinking about it as a sort of debt. My team sees AI as nothing but a positive. Work gets done faster, what's not to like. I think the piper will need to be paid at some point when we look back and realize how a) completely dependent we've become b) unable to reason about our own code base.

I really hope I'm wrong but I can see it already happening.

Post reply on HN