Live data from Hacker News

Nobody knows how to build with AI yet

worksonmymachine.substack.com

161–170 of 432 posts

Re: Nobody knows how to build with AI yet

#161

Earlier quoted context omitted.

Google doesn’t have to change search. It already returns AI generated crap before anything useful.

To be fair, Google also returns a lot of useless crap that wasn't generated by AI.

wasn't generated by their AI, more like

Re: Nobody knows how to build with AI yet

#162

Reading articles like this feels like being in a different reality. I don't work like this, I don't want to work like this and maybe most importantly I don't want to work with somebody who works like this. Also I am scared that any library that I am using through the myriad of dependencies is written like this. On the other hand... if I look at this as some alternate universe where I don't need to directly or indirec…

Genuinely this is what it sounds like to accept obsolescence and I just can’t understand it.

What are you attached to and identify with that you’re rejecting new ways to work?

Change is the only constant and tools now look like superhuman tools created for babies compared to the sota at bell or NASA in the 1960s when they were literally trying to create superhuman computing.

We have more access to powerful compute and it’s never been easier to build your own everything.

What’s the big complaint?

Re: Nobody knows how to build with AI yet

#163

Earlier quoted context omitted.

There is code which is interesting to write, even if it isn't the area with clever algorithms or big architecture decisions or something. But there is also the area of boilerplate, where non-LLM-AI-based IDEs for a few decades already help a lot with templates and "smart" completion. Current AI systems widen that area. The trouble with AI is when you are reaching the boundary of its capabilities. The trivial stuff it…

> But there is also the area of boilerplate, where non-LLM-AI-based IDEs for a few decades already help a lot with templates and "smart" completion. The thing for me is that AI writing the boilerplate feels like the brute force solution, compared to investing in better language and tooling design that may obviate the need for such boilerplate in the first place.

Yeah, but building tooling is a hard sell considering the ability of contemporary AI.

The energy cost is absurdly high for the result, but in current economics, where it's paid by investors not users, it's hidden. Will be interesting to see when AI companies got to the level where they have to make profits and how much optimisation there is to come ...

Re: Nobody knows how to build with AI yet

#164
post #27

Earlier quoted context omitted.

> What junior devs will do, I'm not so sure. They somehow have to jump to the top of the mountain, but the stairs are gone. Exactly my thinking, nearly 50, more than 30 years of experience in early every kind of programming, like you do, I can easily architect/control/adjust the agent to help me produce great code with a very robust architecture. By I do that out of my experience, both in modelling (science) and prog…

I feel like we've been here before, and there was a time when if you're going to be an engineer, you needed to know core equations, take a lot of derivatives, perform mathematical analysis on paper, get results in an understandable form, and come up with solutions. That process may be analogous to what we used to think of as beginning with core data structures and algorithms, design patterns, architecture and infrast…

Exactly right now, I am helping a big oil and gas company have a process simulation software to correctly converge on a big simulation. Full access to the source code, need to improve the Newton method in use with the right line search, validate the derivatives, etc.

I do think that for most of the people, you are right, you do not need to know a lot, but my philosophy was to always understand how the tool you use work (one level deeper), but now the tool is creating a new tool. How do you understand the tool which has been created by your Agent/AI tool?

I find this problem interesting, this is new to me and I will happily look at how our society and the engineering community evolve with these new capacities.

Re: Nobody knows how to build with AI yet

#165

Earlier quoted context omitted.

So many people are hyping AI like it's Musk's FSD, with the same fraudulance in overestimating its capabilities.

it's exactly like this. we're 3 years into being told all white collar jobs are going to be gone next year, just like we're ten years into being told we'll have self driving cars next year

15 years into bitcoin replacing the USD too

Re: Nobody knows how to build with AI yet

#166
post #147
post #56

Earlier quoted context omitted.

People are afraid that instead of skilled craft guild members they will become assembly line workers like Charlie Chaplin in Modern Times. And in 10 years unemployed like people in the Rust Belt.

There's a kind of karmic comedy in this. Programmers' jobs has always been to automate other people's jobs. The panic of programmers about their own jobs now is immensely funny to me. As has been the case for all those jobs changed by programmers, the people who keep an open mind and are willing to learn new ways of working will be fine or even thrive. The people rusted to their seat, who are barely adding value as i…

The problem is that these days we're talking about millions of people.

Those kinds of masses of people don't pivot on a dime.

Re: Nobody knows how to build with AI yet

#167

I'm loving the new programming. I don't know where it goes either, but I like it for now. I'm actually producing code right this moment, where I would normally just relax and do something else. Instead, I'm relaxing and coding. It's great for a senior guy who has been in the business for a long time. Most of my edits nowadays are tedious. If I look at the code and decide I used the wrong pattern originally, I have to…

I also am enjoying LLMs, but I get no joy out of just prompting them again and again. I get so incredibly bored, with a little side of anxiety that I don’t really know how my program works.

I’ll probably get over it, but I’ve been realizing how much fun I get out building something as opposed to just having be built. I used to think all I cared about was results, and now I know that’s not true, so that’s fun!

Of course for the monotonous stuff that I’ve done before or don’t care a lick about, hell yeah I let em run wild. Boilerplate, crud, shell scripts, CSS. Had claude make me a terminal based version of snake. So sick

Re: Nobody knows how to build with AI yet

#168

This article is spot on. I had stumbled upon Kidlin’s Law—“If you can write down the problem clearly, you’re halfway to solving it”. This is a powerful guiding principle in today’s AI-driven world. As natural language becomes our primary interface with technology, clearly articulating challenges not only enhances our communication but also maximizes the potential of AI. The async approach to coding has been most fasc…

Repl.it is so hit or miss for me, and that's that is so frustrating. Like, it can knock out something in minutes that would have taken me an afternoon. That's amazing.

Then other times, I go to create something that is suggested _by them below the prompt box_ and it can't do it properly.

Re: Nobody knows how to build with AI yet

#169

Earlier quoted context omitted.

I know, it's scary. But I guess it's the direction we are aiming for.

Just to clarify, I'm not a member of that "we".

And that's fine, it's your choice. But everything, driven by multiple forces (from hype, to marketing, to real progress, to early adopters) is pointing to that future.

Re: Nobody knows how to build with AI yet

#170
post #14

Earlier quoted context omitted.

> Yes, it's not faster to develop with AI if you watch it work. It’s actually a lot faster. You read the diffs as soon as they start coming in, and immediately course correct or re-prompt when you see bad mistakes.

I don't have this experience. Watching and course correcting like this makes me realize I could have done a better job myself

That’s always true in my experience, but that doesn’t necessarily mean you need to. The trick I’m working towards is refining the workflow such that i can reliably produce maybe 90% as “good” as what I’d personally produce but much, much faster. All sorts of side work I was avoiding before also becomes much easier, less tedious refactors and large test coverage and etc. It can type much faster than I can, the trick is if we can constrain the thinking enough to make it useful. Keeping it as an autocomplete is as productive as it is difficult imo.
Post reply on HN