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

Nobody knows how to build with AI yet

worksonmymachine.substack.com

Post reply on HN
Print view View original

341–350 of 432 posts

Re: Nobody knows how to build with AI yet

#341

Post by divan »

> I'd wander into my office, check what Claude had built, test it real quick. If it worked, great! Commit and push.

Do people read the code? Or just test if it work and push?

To me, code is like a map that has to be clear enough so other humans can read it to navigate the territory (codebase). Even if it's just two – me and AI agent – working on the codebase, it's not much different from "me and another programmer". We both want to have updated mental model of how exactly code structured and how it works and why.

Using AI for coding and not reading the code sounds more like stopping being developer and self-promoting yourself to the manager of AI-programmers who trusts their craft completely.

Re: Nobody knows how to build with AI yet

#342

Post by doom2 »

gronglo wrote: post #220
wiremine wrote: post #138

I've been experimenting with model-based development lately, and this resonated strongly with me. The section "What Even Is Programming Anymore?" hit on a lot of the thoughts and feels I've been going through. I'm using all my 25+ years of experience and CS training, but it's _not_ programming per se. I feel like we're entering an era where we're piloting a set of tools, not hand crafting code. I think a lot of peopl…

> I think a lot of people (who love crafting) will be leaving the industry in the next 5 years, for better or worse. I think you're spot on. It was once necessary to acquire knowledge in order to acquire productivity. This made knowledge valuable and worth attaining. Now, with LLMs, we we can skip the middle man and go straight to the acquisition of productivity. I'd call it the democratisation of knowledge, but it's…

Which makes me wonder: why shouldn't AI use be a core part of technical interviews now? If we're trading "knowledge of how to code" for "knowledge of how to use LLMs" and treating Claude like a much more productive junior engineer, do we still need to filter candidates on their ability to write a doubly linked list? And if we are still asking those sorts of interview questions, why shouldn't candidates be able to use LLMs in the process? After all, like others have said elsewhere in this thread, you still need some core technical capabilities to effectively manage the AI. It's just a tool and we can judge how well someone knows how to use it or not.

Re: Nobody knows how to build with AI yet

#343

Post by gabrieledarrigo »

ath3nd wrote: post #183
gabrieledarrigo wrote: post #169

Earlier quoted context omitted.

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.

Yes, another web3, crypto and nft "inevitable" futures. Just give Sama a couple more trillion and AGI is juuuust behind the corner. It's a fact models aren't getting as cost efficient nor better with the same rate that the costs increases of training and running them. It's also a fact that they are so unprofitable that Anthropic feels like they gotta rug-pull your Claude tokens ( https://news.ycombinator.com/item?id=…

> A future framed as "inevitable" by a bunch of people whose job/wealth depends on framing it as such. Nah, hard pass.

I agree with you! I'm not saying that I like it; this is the perfect example of turbo capitalism applied to innovation.

I also like to code and to build software, and the joy that comes from the act of creation. Only, I'm quite sure it's not going to last.

Re: Nobody knows how to build with AI yet

#344

Post by LtWorf »

pkoird wrote: post #218
d00mB0t wrote: post #38

"I'd wander into my office, check what Claude had built, test it real quick. If it worked, great! Commit and push." Man, I'm going to make so much money as a Cybersecurity Consultant!

Potentially. But also remember what they say about self-driving cars, that it'd make fewer and fewer mistakes than a real driver.

Real drivers would also do fewer mistakes if they only drove in the limited and ideal conditions the self driving cars are limited to.

Re: Nobody knows how to build with AI yet

#345

Post by tcldr »

myblake wrote: post #299
pluc wrote: post #285

Earlier quoted context omitted.

I've always felt building something was close to artistry. You create something out of your thoughts, you shape it how you want and you understand how it works to the most minute detail. The amount of times I've shown something seemingly simple to someone and went "but wait this is what is actually happening in the background!" and started explaining something I thought was cool or clever are great memories to me. AI…

> There's no pride, no joy, just productivity. This is exactly what bothers me about the present moment. Not that the pride of craftsmanship is everything, but dialing it down to zero with extreme pressure to stay that way is a bit sad. But we’ve clearly gone through this with other mediums before, perhaps someday people will appreciate hand written code the way we appreciate hand carved wood. Or perhaps we were all…

I think the audience who can appreciate handcrafted code will be vastly smaller than the audience who appreciates hand carved wood.

Re: Nobody knows how to build with AI yet

#346

Post by jfyi »

rmdashrfv wrote: post #326
gngoo wrote: post #311

To me it feels like I’m in the camp of people who has already figured it out. And I have now learned the hard way that it’s almost impossible to teach others (I organized several meetups on the topic). The ability seems like pure magic. I know that there are others who have it very easy now building even complex software with AI and delivering project after project to clients at record speed at no less of quality as…

> For me it’s just a huge force multiplier, maybe 10-20x of my ability to deliver with my own knowledge and skills on a web dev basis. I can tell you that this claim is where a lot of engineers are getting hung up. People keep saying that they are 10, 20 and sometimes even 100x more productive but it's this hyperbole that is harming that building style more than anything. If you anyone could get 10 to 20 years worth…

I agree. I'd say it's simply that 20 years of software development isn't bottle necked by the ability to churn out code.

Re: Nobody knows how to build with AI yet

#347

Post by j45 »

Loic wrote: post #27
lordnacho wrote: post #15

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…

> 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…

Really well said, it's a large amount of directing in additoin to anything else.

To continue this thought - what could have been different in the last 10-15 years to encourage junior developers to listen more where they might not have to those who were slightly ahead of them?

Re: Nobody knows how to build with AI yet

#348

Post by j45 »

dangero wrote: post #263
lordnacho wrote: post #15

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…

Have you had the realization that you could never go back to dealing with all the minutia again? LLMs have changed me. I want to go outside while they are working and I am jealous of all the young engineers that won’t lose the years I did sitting in front of a screen for 12 hours a day while sometimes making no progress on connecting two black boxes.

Losing first principles will have some kind of an unexpected result.

Like, this is how we've always done it.

Finding a way to better learn first principles compared to sitting in front of a screen for 12 hours a days is important.

Re: Nobody knows how to build with AI yet

#349

Post by Anon1096 »

Sammi wrote: post #319
real-hacker wrote: post #318

Earlier quoted context omitted.

The spec, or prompts system, whatever you call it, is more like a recipe than code. It doesn't automatically generate the dishes; a good cook is still needed.

Yes and culinary schools exist and create new cooks in a reproducible way. Why can't coding with ai be taught?

I disagree with the OP that AI coding can't be taught. My answer to why so many people have trouble would be that they refuse to learn. I see tons of people who are insanely biased against AI and then when they try and use it they give up after the first go (having tried a horrible application of AI like making a functioning production app with 1 single prompt, no one using AI for work is using it like that). They also don't take any suggestions on using it better because "I've tried it before and it sucked."

If you asked me months ago whether "prompt engineering" was a skill I'd have said absolutely not, it's no different than using stack overflow and writing tickets, but having watched otherwise skilled devs flounder I might have to admit there is some sort of skill needed.

Re: Nobody knows how to build with AI yet

#350

Post by MITSardine »

lelanthran wrote: post #292
NitpickLawyer wrote: post #284

Earlier quoted context omitted.

> Those young engineers, in 10 years, won't be able to fix what the LLM gave them,because they have not learned anything about programming. I have heard a version of this plenty of times, and it was never correct. In the early 90s it was the "electronics" people that were saying "I come from an electronics background, these young'uns will look at a computer and don't know what to do if it breaks". Well, bob, we did,…

Have you also heard about calculators? Every single finance person uses a calculator. How effective do you think a person in any aspect of finance would be if they had never learned what multiplication is? Would they perform their job adequately if they don't know that `X * Y` is `X repeated Y times`? IOW, if you gave a finance person (accountant, asset manager, whatever) a non-deterministic calculator for multiplica…

If I may play the devil's advocate, nothing is deterministic. A neutrino could cause a bit flip in your calculator. More commonly, the lower abstractions we build upon without knowing their innards can have bugs. Even the most popular compilers (say, g++) have bugs, for instance. I am personally incapable of fixing a bug within gcc, despite the tool being a vital requirement of my work.

IMO the dichotomy should not be deterministic/stochastic, but proved/unproved reliable. gcc has been shown reliable, for instance, so I don't need to know whether it was built by deterministic (clever engineers) or stochastic (typewriting monkeys) processes. I'm certain the former are more efficient, but this is ultimately not what makes the tool valuable.

As a bit of an artificial example, there's stochastic processes that can be proved to converge to a desired result (say, a stochastic gradient descent, or Monte-Carlo integration), in the same way that deterministic methods can (say a classic gradient descent or quadrature rules).

In practical cases, the only proof that matters is empirical. I write (deterministic) mathematical algorithms for a living, yet they very rarely come out correct on first iteration. The fact there is a mathematical proof that a certain algorithm yields certain results lets me arrive at a working program much faster than if I left it to typewriting monkeys, but it is ultimately not what guarantees a valid program. I could just as well, given enough time, let a random text file generator write the programs, and do the same testing I do currently, it would just be very inefficient (an understatement).

Post reply on HN