Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Coding expertise is going to collapse from AI reliance

larsfaye.com

Post reply on HN
Print view View original

481–490 of 575 posts

Re: Coding expertise is going to collapse from AI reliance

#481

Post by 10000truths »

apatheticonion wrote: post #415

I see a large emphasis placed on headless agentic/vibe coding, what I don't see people talking about is how great guided coding is. I have over a 15 YoE writing software and guided coding sessions - that is, using an editor like Zed or VSCode with an LLM integrated, writing code how you normally would but using a flash model to prompt away the annoying parts and/or plan - is as productive as vibe coding, produces sig…

Headless agentic coding only works when:

* The scope is constrained and clearly defined

* You articulate an exhaustive and objective set of success criteria

* You provide a deterministic tool for the AI to evaluate its output against those criteria and receive feedback (compiler errors, unit tests, regression tests, etc.)

You're essentially writing a comprehensive spec for the AI to follow. The time suck was always from making the spec and the QA bulletproof.

Re: Coding expertise is going to collapse from AI reliance

#482

Post by apatheticonion »

10000truths wrote: post #481
apatheticonion wrote: post #415

I see a large emphasis placed on headless agentic/vibe coding, what I don't see people talking about is how great guided coding is. I have over a 15 YoE writing software and guided coding sessions - that is, using an editor like Zed or VSCode with an LLM integrated, writing code how you normally would but using a flash model to prompt away the annoying parts and/or plan - is as productive as vibe coding, produces sig…

Headless agentic coding only works when: * The scope is constrained and clearly defined * You articulate an exhaustive and objective set of success criteria * You provide a deterministic tool for the AI to evaluate its output against those criteria and receive feedback (compiler errors, unit tests, regression tests, etc.) You're essentially writing a comprehensive spec for the AI to follow. The time suck was always f…

Even then, it tends to code itself into a corner. Code tends to be ridged and difficult to expand.

One shot benchmarks that have exhaustive prompts are impressive, but benchmarks that emulate real software development (iterative changes over time with changing requirements) have close-to-zero pass rates.

Re: Coding expertise is going to collapse from AI reliance

#483

Post by mekael »

monkaiju wrote: post #471
Seattle3503 wrote: post #465

Earlier quoted context omitted.

Where do you work where there isn't pressure to use agents?

Where I work we actively ban LLM use in development. We're hiring too so if you're willing to live in Salt Lake City...

May i ask what industry youre in? Also, how’s the winter in SLC?

Re: Coding expertise is going to collapse from AI reliance

#484

Post by vermilingua »

roblh wrote: post #378
LandoCalrissian wrote: post #54

The snake eating it's own tail for llm software development has really been met with a shoulder shrug whenever it gets brought up. At best you might have a small cohort of developers that don't cook their brains with AI and their reward for that appears to be having to review terrible AI code written by people who have cooked their brains. Completely unsustainable.

Maybe I’m naive, or misguided, or something else, but I decided almost 2 years ago that I’m going to bank on not using LLMs to do my job. I still write code by hand everyday. I don’t use AI to write code or lookup docs, or anything else. I just figure that if we really, truly, indisputably hit the point of AI assisted coding being mandatory, I can learn it and get up to speed in a few weeks (or at worst a couple mont…

I am in exactly the same position; I don't feel left behind per se but I was just fired for my stance. Management is entirely deluded across the industry, and in my case it was even acknowledged and agreed that my output and the quality of work was not in question, simply the fact that I didn't use LLMs to produce it.

I reckon everything needs another 6-18 months to ripen, then those of us who haven't bet the farm on slop will be in big business contracting and consulting to drag companies out of the pit they're digging themselves.

Re: Coding expertise is going to collapse from AI reliance

#485

Post by 10000truths »

apatheticonion wrote: post #482
10000truths wrote: post #481

Earlier quoted context omitted.

Headless agentic coding only works when: * The scope is constrained and clearly defined * You articulate an exhaustive and objective set of success criteria * You provide a deterministic tool for the AI to evaluate its output against those criteria and receive feedback (compiler errors, unit tests, regression tests, etc.) You're essentially writing a comprehensive spec for the AI to follow. The time suck was always f…

Even then, it tends to code itself into a corner. Code tends to be ridged and difficult to expand. One shot benchmarks that have exhaustive prompts are impressive, but benchmarks that emulate real software development (iterative changes over time with changing requirements) have close-to-zero pass rates.

Well yes, if the thing you're working on is subject to changes in requirements, then you fundamentally can't one-shot it, AI or no AI. That's why the waterfall process fell out of fashion long ago.

But there are cases where there are no changes, or only backwards-compatible changes. Take the core WebAssembly specification, for example. Extremely detailed, formally verified, comes with a large test suite. Someone else has done the hard work of specifying the behavior of every possible edge case. A WASM runtime implementer can point their agent to that spec, plus some prior art. The remaining manual work is in constructing a test harness and collecting a corpus of test WASM binaries that exercises decent coverage.

Re: Coding expertise is going to collapse from AI reliance

#486

Post by massagedpelican »

DanHulton wrote: post #371
skydhash wrote: post #168

Earlier quoted context omitted.

> History is littered with similar cases where the abstraction layer ends up getting lifted, and people struggle with getting accustomed to working at that higher abstraction level. But there's no abstraction layer that ends up getting lifted. When I use a library like SDL or a standard like POSIX, I don't tend to look at the underlying implementation. Instead I work with the high level concepts that they come up wit…

Exactly this. You still have to understand the abstraction layer the LLM is working at in order to be able to form an opinion about the quality of the code. (If you DON’T care about the quality of the code, there’s always been ways to get an extra 1000% short-term speed improvement by just not giving a shit.) AI isn’t “a code abstraction layer” any more than Jira is, or the engineer themselves is.

I think "the engineer themselves" is much closer to the abstraction layer I'm referring to.

Imagine for a moment that, rather than using a compiler to translate c++ into assembly, that it instead has to be done by a person on the team. If that were the case, the resulting assembly code would certainly have to be reviewed and assessed before it was accepted.

Why?

Because people can also be leaky, non-deterministic abstraction layers. The only reason that the output of a compiler isn't regularly reviewed (in 99% of cases) is because it's extraordinarily reliable and consistently correct, or correct enough for most cases.

It's not terribly dissimilar from delegating engineering tasks to other engineers. When I ask someone else to develop one component of a larger application, I'm not telling them exactly what lines to write, I'm giving them some kind of structure and they're filling in the rest. The communication to them is above the implementation layer.

Agents are increasingly letting us work at that same boundary. Just because the current state of LLMs requires engineering knowledge to review the result doesn't mean an abstraction hasn't occurred. It speaks more to the current quality of that abstraction than the absence of one.

I think that if LLMs were able to achieve the same consistency as a compiler, most people wouldn't ever bother to check the underlying code it produced. I also think it would be difficult to not acknowledge that LLMs have gotten better at converting natural language into functioning software. The abstraction is certainly not perfect, but it is clearly improving.

Re: Coding expertise is going to collapse from AI reliance

#487

Post by rcr-anti »

I work in higher ed and have been involved in "how do we use this to help people learn" efforts since gpt 3.5 days. The method most reliable and with the best results has been treating LLMs like a glorified interface to classic expert systems. Boring state machine, problem sets and sometimes procedural generation of problems, instructor selected groupings and "hint" policy. Other applications have been building simulations, usually for chem, physics, bio, and giving an in browser agent access to the same interface as the student. Idea being this allows a flow of making predictions and observing results, demonstrating or clarifying a specific point. Counter intuitively it's made creating course material far more laborious, since we have to lay out everything much more thoroughly, plus subject matter experts have to translate it to programmers and back, versus an instructor attempting to teach inherently from their already-expert point of view.

Re: Coding expertise is going to collapse from AI reliance

#488

Post by foltik »

xtracto wrote: post #309

Yes, and it doesn't matter. Writing code in programming languages is a skill/necessity created by us to instruct computers what we want them to do Initially in the 60s, this was done by connecting circuits one way or another (think ENIAC). Then we devised "programmable" computers and devised a bunch of codes (computer code instructions) that abstracted away those cables. The we created Programming Languages to furthe…

Computers are useful because we can instruct them what we want to do precisely.

It’s true we usually don’t care about all the details, which is why abstractions exist. An abstraction hides details by fixing them, and lets you specify the rest precisely.

An LLM isn’t an abstraction in this sense any more than asking a coworker to do something is. The details are not fixed, but decided for you. If you can’t understand or modify what was decided yourself, the only interface left is going back and forth in natural language.

So no, the abstractions won’t become unnecessary. The details don’t just go away. Plenty of people really don’t care about them, and for them the LLM is fine, but only because it’s gluing together the millions of LoC of existing libraries and frameworks where the details have already been fixed, overwhelmingly by humans.

There will always be a need for human professionals who aftually understand all that obscure stuff, and per TFA, it’s looking like it won’t be the ones who went all in on AI.

Re: Coding expertise is going to collapse from AI reliance

#489

Post by shadowgovt »

As it stands today, probably.

Whether that actually has negative consequences is the more interesting question I think. Higher level languages collapsed understanding of CPU architecture and assembly level programming.

But as a result, we are writing more programs, not fewer, since we're operating at a layer of abstraction that matches closer to human thought process than what is dictated by the mechanisms of the underlying machine.

Re: Coding expertise is going to collapse from AI reliance

#490

Post by whattheheckheck »

hirvi74 wrote: post #360
hintymad wrote: post #275

Earlier quoted context omitted.

> The coding part of my career is over. LLMs are capable of doing everything I've ever been paid to write . Remember we used to spend enormous amount of time in school and in our spare time studying computer science? Algorithms, operating systems, compilers, and etc. All kinds of insights. All kinds of fun. All kinds of hard engineering. Yet, how much time do we really need to spend in our day-to-day work implementin…

> Remember we used to spend enormous amount of time in school and in our spare time studying computer science? Algorithms, operating systems, compilers, and etc. All kinds of insights. All kinds of fun. All kinds of hard engineering. Yet, how much time do we really need to spend in our day-to-day work implementing or using the algorithms and etc that we have learned? Because great insight and expertise stems from fou…

So what drills do you practice
Post reply on HN