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

201–210 of 403 posts

Re: Agentic Coding Is a Trap

#201

Post by notepad0x90 »

andrekandre wrote: post #98
notepad0x90 wrote: post #50

it's a fairly new way of doing things. I predict, in the future it will be more formalized and standardized like AGILE and SCRUM and all that boring stuff. The result of that though would be establishment of development patterns that are good practices. The rule of thumb is: An agent can write it, but a human has to understand it before it gets pushed to prod. I'm still not convinced about the doom and gloom over dev…

> 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".

Re: Agentic Coding Is a Trap

#203

Post by ytoawwhra92 »

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…

> 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, decide who's doing the work. That all can take days or even weeks. Then you need to write a design doc with your proposed design, and get that reviewed by your peers/teammates. Again, another week for any substantial feature. If there are multiple teams involved, you need to get buy-in and design agreement among those multiple teams, let's add another week. At some places, you need approval to commence work, which can take multiple days, depending on the approver's schedule and availability.

All the process you described exists to maximise the amount of time your software engineers spend writing code[0]. You put this process in place because software engineers are among the most expensive employees in the business. Their time being wasted is meaningful to the bottom line.

Make the software engineers cheap enough and the need for a lot of this process evaporates. Companies that already _have_ these processes in place will be SOL because it's incredibly challenging to break a bureaucracy like that, but companies that either don't have these processes or manage to eliminate them will have a significant competitive advantage.

Which shouldn't be news. Startups have always competed with established businesses via speed of execution. What's new is the ability to maintain that speed for longer.

> At bigger companies, you're going to need to pass all sorts of reviews from other departments, like legal, privacy, performance, accessibility, QA...

These are all in the firing line. If the company could outsource their legal liability to an external provider of these reviews, they would.

[0] We'll just ignore the irony that much of this process ends up being foisted on the employees whose time you're hoping to save.

Re: Agentic Coding Is a Trap

#204

Post by fatata123 »

bhagyeshsp wrote: post #181
sterlind wrote: post #160

Earlier quoted context omitted.

accelerated what learning? learning to code? learning to engineer? learning to manage? learning to market?

Learning the fundamentals of programming and their translation to code. I'm decent at engineering, managing and marketing solutions.

[dead]

Re: Agentic Coding Is a Trap

#205

Post by Terr_ »

grogenaut wrote: post #57
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.…

Agreed. I don't know anything about turning sand into transistors or assembly but do well. So I don't know my full stack either. What is important is not being afraid to learn the rest of your system and keeping an index. Most importantly it's about being able to spin up on anything quickly. That's how you have wide reach. Digging in when you have to, gliding high when you have to. Appropriate level for the problem a…

[dead]

Re: Agentic Coding Is a Trap

#206

Post by Terr_ »

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…

> too fast

Another aspect is that it reorders some of our problems.

In typical development, we're more likely to go back and forth about "is this really what we want to make" or "what could possibly go wrong if we do that", and ideally we do it before PR's get approved or anything is merged/deployed. Some portion of that is getting moved to "we'll see if anyone complains later". As they say, an ounce of prevention is worth a pound of cure.

Re: Agentic Coding Is a Trap

#207

Post by otabdeveloper4 »

chaidhat wrote: post #149
keyle wrote: post #79

As a senior developer, 25+ years, I have been thrown recently into a meeting "hey can you join in for 5 mins". I really don't like these meetings where you're dragged in in the middle of them without any clue. The questions came flying in fast, without any introduction, and this was about an external integration out of a dozen. They have their own lingo, different from ours, to make the situation worse. I had a _very…

I think that in an AI-native company, the people asking the question should be using their own set of the AI to query the codebase, before coming to ask you. The problem that you describe seems to be more relevant to an organization which has not fully embraced AI yet.

> AI-native company

No such thing. The AI hype bubble is only a couple years old, and will not last a couple years more.

Re: Agentic Coding Is a Trap

#208

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…

> 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. The nature of the code will mitigate "catastrophe" to a small group at worst, but most likely initial rollout will just run new versions of the code in a simulated context (language design could benefit from this) and analyze potential outcomes without affecting current functionality.

But when the code goes live... it will be slowly scope changes progressively (think feature/experiment flags) and if it fails in the initial cohort, it will redirect. If success is positive, it will increase the rollout cohort.

This is a normal software engineering practice today, but it's labor and process intensive when driven by humans. But in a world where humans are less involved, this process is scalable.

Re: Agentic Coding Is a Trap

#209

Post by otabdeveloper4 »

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…

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.

Re: Agentic Coding Is a Trap

#210

Post by svnt »

fnordpiglet wrote: post #174
catlifeonmars wrote: post #153

Earlier quoted context omitted.

> The claim you should know everything about everything you work on is an intensely naive one. I disagree with this take. Personally, I pride myself in learning the code bases I work on in detail, sometimes better than the leads for those code bases. I’m not saying that everyone should do so, but it’s achievable and not naive at all.

Knowing it better than the leads isn’t that hard - they spend most their life in meetings and teaching people how to think. Knowing the code base in detail is important - but I’m certain unless you wrote it all, there are parts you don’t know. I’m sure what you do is build enough scaffold understanding and depth in the core parts you can visit any part and understand it. But I’m also certain there are parts that base…

Even if you did write it all, unless you are regularly in all of it (which sounds like a horrible job to me), or it is rather small, in my experience you will be at some point trying to git blame some section of code you don’t understand only to find the finger pointed at your ghost.
Post reply on HN