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

I don't think AI will make your processes go faster

frederickvanbrabant.com

Post reply on HN
Print view View original

201–210 of 490 posts

Re: I don't think AI will make your processes go faster

#201

Post by ethin »

BugsJustFindMe wrote: post #108
satvikpendem wrote: post #102

Earlier quoted context omitted.

The PMs validate it, why do you think they don't read over it to make sure it fits what they want? You might say "well they're lazy, look why they didn't write enough detail to start off with" but for lots of people, reviewing something to make sure it's close to what they want and then tweaking it is much easier than writing it from scratch. It's the equivalent of writer's block and is why a common advice given to w…

> The PMs validate it, why do you think they don't read over it to make sure it fits what they want? Hahahahahaha. Sorry, I couldn't help myself; this reads like satire. The answer is "real life experience says otherwise".

Yeah I was so tempted to ask if this person has ever actually met a project/product manager...

Re: I don't think AI will make your processes go faster

#202

Post by Cthulhu_ »

angarg12 wrote: post #189

> This exact thing is what software developers have been begging for since the beginning of the profession: Receiving a detailed outline of the problem and what the end result should look like. > This is often the part that slows down software development. Trying to figure out what a vague, title only, feature request actually means. But that is exactly what Software Engineering is!. It's 2026 and the notion that you…

I'm seeing decision-makers / people who write requirements starting to use AI as well in my day to day. As before, my job is to read, understand and test those requirements against the real world as I understand it. But same with code. Software engineering for the past (at least) 20 years has had a core focus of "don't trust anyone", this hasn't changed and this takes a lot of time and effort still.

Re: I don't think AI will make your processes go faster

#203

Post by pron »

SirHumphrey wrote: post #200
pron wrote: post #197

Earlier quoted context omitted.

> It's 2026 and the notion that you can get detailed enough requirements and specifications that you can one-shot a perfect solution needs to die. It's 2026 and the idea that even with detailed-enough requirements you can one-shot even a workable (let alone perfect) solution also needs to die. Anthropic failed to build even something as simple as a workable C compiler, not only with a perfect spec ( and reference imp…

Most software is much simpler than a c compiler.

A workable C compiler is a ~10-50KLOC program, and a fairly simple one at that (batch, with no concurrency or interaction). That Anthropic's swarm of agents wrote 100KLOC before failing is a symptom of the problem. It's certainly possible that many programs are in the sub 5KLOC range, but it's definitely not "most software". Plus, almost no software has this level of detailed spec, ready-made tests, and a selection of existing implementations of the same spec.

My first thought when reading Anthropic's description of the experiment was that it is unrealistically easy. It's hard to come up with realistic jobs in the 10-50KLOC range that would be this easy for an LLM. That it failed only shows how much further we still have to go.

Re: I don't think AI will make your processes go faster

#204

Post by majormajor »

convolvatron wrote: post #160
majormajor wrote: post #140

Earlier quoted context omitted.

I don't think that works as a critique of LLMs because it's far too broadly applicable to well-accepted tools. Are advanced calculators bad because a student could use the CAS to ace calculus homework, exams or the SAT without actually learning the material? Is copy/paste bad because a person could use it to copy/paste code from one place to another without noticing some of the areas they need to update in the new lo…

but in this case that's exactly what AI is doing, and no more. its filling in the gaps with some plausible sounding goo so that the person doesn't have to worry about the details. ok, so for some of the jobs we're doing plausible sounding goo is just fine. and that's kinda sad. but the 'just playing around' case is fine for PSG, this isn't a serious effort but just seeing how things might work out without much effort…

I don't disagree with your take on most jobs or vibe coding as shown in countless proof-of-concept/0-to-1 demos. But the comment I was replying to was dismissing this statement from another commenter:

> People who use AI because they are trying to avoid doing work fall into a completely different category than people using AI as a force multiplier and for skills/capabilities enhancements / quality improvement.

This statement is absolutely true. There are ways to use LLM tools to significantly improve the quality of your work instead of to avoid doing hard work. (And the result can easily become something that requires more hard thought, not less.)

Some that I frequently enjoy that are usable even if you don't want the machine to generate your actual code at all: * consistency-check passes asking it to look for issues or edge cases * evaluation of test coverage to suggest any missed tests or proposed new ones * evaluation of feasibility of different refactoring approaches (chasing down dependencies and call trees much more faster than I would be able to do by hand, etc)

> to the extent to which coding is the production of boilerplate is really a problem with APIs and abstraction design. if we can get LLMs to mitigate some of that I the short term without causing too much distraction, that's fine, but we should really be using that to inform the solution to the fundamental problem.

I generally would disagree with this, though. I don't think there's solely a problem with abstraction design, I think the inherent complexity of many systems in the business world is very high (though obviously different implementations make it different levels of painful). If that's a problem, it's a people/social one, not a technology problem.

In my future we lean into the fact that people want features, they want complexity, for many things - everybody's ideal just-for-them workflow/tooling would look slightly different than the next person's - and use these tools to build things that do more, not less. Like the evolution of spellcheck from something you manually ran, to something that constantly ran, to something that can autocorrect generaly-usefully when typing on a touchscreen.

Let's get back to finding more features/customization to delight users with.

Re: I don't think AI will make your processes go faster

#205

Post by netcan »

>What people typically don’t do is look at why this is taking so long, and even more importantly: long duration does not automatically mean the problem originates there.

To some extent, we tell as many lies as we can get away with. Some answers are more convenient then others.

"Why" this is taking so long, like "why did this fail?" are prone to broadly agreed lies. Sometimes this is for obvious blame liability reasons. Often, this is because the lie conflicts with some "meta."

One such fallacy is the idea that software=value. Code= money, because it cost money to write. Features=revenue. Etc.

Irl.. startups produce features very quickly because they actually need features. They start with zero features.

But... LinkedIn, visa or even Facebook.... What they are short on is opportunities to develop code with value. Ie... Something that will increase revenue.

FB aren't resource constrained. They're demand constrained. If there were a "write code, make revenue" opportunity available... they'd have taken it already.

This totally conflicts with the experience of working somewhere. That's because you have wishlists, road maps and deadlines.... and it always appears that demand for code is sky high.

Re: I don't think AI will make your processes go faster

#206

Post by tedd4u »

whstl wrote: post #129
phyzix5761 wrote: post #12

I think when LLMs first came out people thought they could just say something like, "Make a Facebook clone". But now we're realizing we need to be more exact with our requirements and define things better. That has always been the bottle neck in software. When I was working we used to get requirements that literally said things like, "Get data and give it to the user". No definition of what data is, where its stored,…

This was already a reality for a years. In several companies I have seen product managers joining teams and failing to even have minor requirement ready for months during “onboarding” of the PM. And then code being ready but taking months to release because DevOps is busy or QA can’t find time. The pace of release of software has been disconnected from the coding part for the longest time, and we have been quiet abou…

The solution I've seen work is have engineers and designers that can take much of the detailed spec writing on, and have the PMs spend time with users/prospective users, partners, etc, understanding the market and users better. When you pull PMs in to all the details, often they turn into project managers, shuffling bug tickets around etc, taking time away from owning the user and the problem and shifting them too much to the solution side. Have a lead engineer own much / most of that. Every org / product is different of course.

Re: I don't think AI will make your processes go faster

#207

Post by derefr »

phyzix5761 wrote: post #12

I think when LLMs first came out people thought they could just say something like, "Make a Facebook clone". But now we're realizing we need to be more exact with our requirements and define things better. That has always been the bottle neck in software. When I was working we used to get requirements that literally said things like, "Get data and give it to the user". No definition of what data is, where its stored,…

> I think when LLMs first came out people thought they could just say something like, "Make a Facebook clone". But now we're realizing we need to be more exact with our requirements and define things better.

The annoying thing is that giving an LLM vague instructions like "make a Facebook clone" does work... in certain limited cases. Those being mostly the exact things a not-very-creative "ideas person" would think to try first. Which gave the "ideas people" totally the wrong idea about what these things can do.

These same "ideas people" have been contracting human software developers to "make them a Facebook clone" (and other requests of similar quality) for decades now.

And every so often, the result of one of those requests would end up out there on the internet; most recently on Github. (Which is, once there's enough of them laying about, already enough to allow a coding-agent LLM trained on Github sources to spew out a gestalt reconstruction of these attempts. For better or worse.)

But for the most common of these harebrained ideas (both social-media-feed websites and e-commerce marketplace websites fit here), entire frameworks or "engines" have also been developed to make shipping one of these derivative projects as easy as shipping a Wordpress.org site. You don't rewrite the code; you just use the engine.

And so, if you ask an LLM to build you Facebook, it won't build you Facebook from scratch. It'll just pull in one of those frameworks.

And if you're an "ideas person", you'll think the LLM just did something magical. You won't necessarily understand what a library ecosystem even is; you won't realize the LLM didn't just generate all the code that powers the site itself, spitting out something perfectly functional after just a minute.

Re: I don't think AI will make your processes go faster

#208

Post by binary0010 »

SirHumphrey wrote: post #200
pron wrote: post #197

Earlier quoted context omitted.

> It's 2026 and the notion that you can get detailed enough requirements and specifications that you can one-shot a perfect solution needs to die. It's 2026 and the idea that even with detailed-enough requirements you can one-shot even a workable (let alone perfect) solution also needs to die. Anthropic failed to build even something as simple as a workable C compiler, not only with a perfect spec ( and reference imp…

Most software is much simpler than a c compiler.

Not really.

I can make a c compiler in a couple weeks just by looking up open source libraries and copying them.

I can't make any software that people will pay me money to use without taking months/years of development, research, expiramentation and iteration.

Just because the original people who invented compilers had to be genius, doesn't mean anyone has to spend much time or thought in copying that work now.

Re: I don't think AI will make your processes go faster

#209

Post by rockbruno »

phyzix5761 wrote: post #12

I think when LLMs first came out people thought they could just say something like, "Make a Facebook clone". But now we're realizing we need to be more exact with our requirements and define things better. That has always been the bottle neck in software. When I was working we used to get requirements that literally said things like, "Get data and give it to the user". No definition of what data is, where its stored,…

Realizing? Will be very happy if that is the case, but in my view all big company execs are still balls deep into the notion that you will be able to just ask it for the facebook clone and everything sucks as a result

Re: I don't think AI will make your processes go faster

#210

Post by quantumleaper »

pron wrote: post #203
SirHumphrey wrote: post #200

Earlier quoted context omitted.

Most software is much simpler than a c compiler.

A workable C compiler is a ~10-50KLOC program, and a fairly simple one at that (batch, with no concurrency or interaction). That Anthropic's swarm of agents wrote 100KLOC before failing is a symptom of the problem. It's certainly possible that many programs are in the sub 5KLOC range, but it's definitely not "most software". Plus, almost no software has this level of detailed spec, ready-made tests, and a selection o…

A bit off topic, but see how Anthropic publicity stunts went from "Claude C Compiler" with 100K LOC to the recent Bun Rust rewrite with 1M LOC (10x!) in just 3 months.

I get that it's "novel" creation vs porting, but given that they reported that the C compiler cost them $20k in API costs, the Bun rewrite must be at least $200k, maybe even closer to a million. Pure madness.

Post reply on HN