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

211–220 of 403 posts

Re: Agentic Coding Is a Trap

#211

Post by deweywsu »

FridgeSeal wrote: post #167
danenania wrote: post #152

Earlier quoted context omitted.

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 perspectiv…

This is what I have been thinking. Business will always try to do more with less because their only true goal is figuring out how to make more money. They will sacrifice giving those juniors time to learn from their mistakes for the sake of making more widgets (code). From the wider generational view, they will rob today's juniors from the chance to learn and thereby keep the talent pipeline full so they can profit today, the future (and the developers who will arrive there) be damned. The economic game is flawed because it only ever comes down to a single output that is optimized for: money. One solution? I think software people might consider forming unions. I know that's antithetical to the lone coder ethos, but if what this comment reflects is true, the industry needs a check and balance to prevent it from destroying its foundation from the inside.

Re: Agentic Coding Is a Trap

#212

Post by helloplanets »

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.

Re: Agentic Coding Is a Trap

#213

Post by dilyevsky »

otabdeveloper4 wrote: post #209
SpicyLemonZest wrote: post #157

Earlier quoted context omitted.

> 1. models are now extremely good at totally automating tedious tasks such as updating dependancies, build/deploys scripts, unit tests, etc what used to take days now can takes minutes. Easily 50x speedup on this. This was non-trivial part of every engineer's day-to-day at an established company. "platform engineering" or whatever they call this now is dead. I confess that I don't understand why this isn't true, bec…

Because "platform engineering" isn't about writing bash scripts, it's about having a mental model of the system architecture. (Which the LLM definitely doesn't have.) Also, it's always the case where you think LLMs are great at doing whatever it is that you don't understand or value.

There was lot of lofty ideas around devops/pe and the like but ime the grim reality is that in most of managers’ heads it’s basically “tools that product engs don’t want to be concerned with” and like i said current models are really really good at this. Also disagree on the mental model thing - give opus 4.7 or latest codex access to your code, design mds and your logging mcp - in five minutes it will be better at debugging production issues than 90% of platform engineers I’ve worked with. It is truly over

Re: Agentic Coding Is a Trap

#214

Post by dilyevsky »

WorldMaker wrote: post #184
dilyevsky wrote: post #132

Earlier quoted context omitted.

Respectfully, unless someone is really really bad at articulating what the quality standards are or works with a very niche stack that is definitely not the case anymore with SOTA models

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

Re: Agentic Coding Is a Trap

#215

Post by throwaway041207 »

bulbar wrote: post #198
throwaway041207 wrote: post #133

Earlier quoted context omitted.

IMO, by the time todays juniors would have 5-10 years of expected experience, the entire field will be something different altogether. Language choice distribution will collapse (if not change altogether), whole new modalities of monitoring and progressive delivery guardrails will come into play, essentially creating a 24/7 incremental rollout of pure agentic code, correctness will be determined by a mix of language…

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 yet the wheel turns despite their treasured insights.

Re: Agentic Coding Is a Trap

#216

Post by ehnto »

wiieee wrote: post #163
zbentley wrote: post #143

Earlier quoted context omitted.

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.

I don't know if it really plays out like that, though I hope so. Many businesses are mega successful in spite of incredibly poor or inefficient technical execution. I don't know if it really matters so long as customers get the thing they want for the price they're willing to pay.

I think this matters even less in higher tech companies, because they're not playing in the margins where an inefficiency can hurt. Though perhaps ironically, I think AI providers really are in a realm where technical execution at the margins will make or break them.

Re: Agentic Coding Is a Trap

#217

Post by bulbar »

throwaway041207 wrote: post #208
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…

> 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". What I think will happen is AI will write code and it will do the best it can to mitigate mistakes prior to rollout, but once rollout time occurs, rollout will be incremental and it will self monitor by defining success conditions at rollout time.…

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 example.

Re: Agentic Coding Is a Trap

#218

Post by dilyevsky »

SpicyLemonZest wrote: post #157
dilyevsky wrote: post #150

Earlier quoted context omitted.

1. models are now extremely good at totally automating tedious tasks such as updating dependancies, build/deploys scripts, unit tests, etc what used to take days now can takes minutes. Easily 50x speedup on this. This was non-trivial part of every engineer's day-to-day at an established company. "platform engineering" or whatever they call this now is dead. 2. technically risky ideas that you never would have tried b…

> 1. models are now extremely good at totally automating tedious tasks such as updating dependancies, build/deploys scripts, unit tests, etc what used to take days now can takes minutes. Easily 50x speedup on this. This was non-trivial part of every engineer's day-to-day at an established company. "platform engineering" or whatever they call this now is dead. I confess that I don't understand why this isn't true, bec…

I think it’s because most PEs are in general conservative (the whole “mr no” meme) and also have limited experience writing software so they will be slow to adapt to this paradigm shift

Re: Agentic Coding Is a Trap

#219

Post by nyssos »

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.

I do this for debugging. Models are extremely vulnerable to framing effects and it's usually easier to spin up a fresh instance than it is to get an existing one to generate new hypotheses.

Re: Agentic Coding Is a Trap

#220

Post by nyssos »

dilyevsky wrote: post #132
kelnos wrote: post #64

Earlier quoted context omitted.

IME, it's faster and less frustrating to just write the code myself, if the goal is to get code to my quality standards.

Respectfully, unless someone is really really bad at articulating what the quality standards are or works with a very niche stack that is definitely not the case anymore with SOTA models

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.

Post reply on HN