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

321–330 of 432 posts

Re: Nobody knows how to build with AI yet

#321

Post by intrasight »

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 fully expect that in 1-2 years that SWE curriculum will have AI coding as a major feature. The question I have is will students be required to do their first year or first assignments in a given course without AI.

My ex teaches UX. We were talking about AI in academia last week. She said that she requires students to not use AI on their first assignment but on subsequent ones they are permitted to.

Re: Nobody knows how to build with AI yet

#322

Post by fullstackchris »

Flatcircle wrote: post #22

My theory on AI is it's the next iteration of google search, a better more conversational, base layer over all the information that exists on the internet. Of course some people will lose jobs just like what happened to several industries when search became ubiquitous. (newspapers, phone books, encyclopedias, travel agents) But IMHO this isn't the existential crisis people think it is. It's just a tool. Smart, clever…

This comment makes no sense here. Did you read the article? The author built an entire SaaS app in a few days with an agent. That isn't "just search"

Re: Nobody knows how to build with AI yet

#323

Post by brap »

I don’t know which models you guys are working with, but all of the SOTA ones I’ve tried in different configurations ended up producing mostly garbage.

I find myself having to spend more time guiding the model in the right direction and fixing its mistakes than I would’ve spent building it all myself.

Every time I read one of these stories I feel like maybe you guys have models from 2035, because the ones we have today seem to be useless outside of creating greenfield, simple React apps that just sort of work.

One thing I’ll say is that it’s been a real time saver for debugging. For coding, a huge waste of time. Even for tasks that are menial, repetitive, require no thinking etc. I find that it’s mostly crap.

Re: Nobody knows how to build with AI yet

#324

Post by rightbyte »

JSteph22 wrote: post #100
aDyslecticCrow wrote: post #50

Earlier quoted context omitted.

As search gives the answer rather than the path to it, the job of finding things out properly and writing it down for others is lost. If we let that be lost, then we will all be lost. If we cannot find a way to redirect income from AI back to the creators of the information they rehash (such as good and honest journalism), a critical load-bearing pillar of democratic society will collapse. The news industry has been…

I am looking forward to the "news industry" breathing its last breath. They're the ones primarily responsible for the distrust and division.

My take is that journalists, was fighting enshittification as long as they could one looming bankruptcy leading to consolidation or closed shop at a time.

Re: Nobody knows how to build with AI yet

#325

Post by sgt101 »

So far:

- when I ask models to do defined that I know how to do and can tell them about that method but can't remember the details off off hand and then I check the answers things work.

- when I attempt to specify things that I don't understand fully the model creates rubbish 7 out of 10 times, and those episodes are irretrievable. About 30% of the time I get a hint of what I should do and can make some progress.

Re: Nobody knows how to build with AI yet

#326

Post by rmdashrfv »

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 of work done in 1 year, it would be so obvious that you wouldn't even have to tell anyone. Everyone would just see how much work you got done and be like "How did you do 2 decades worth of work this year?!"

Re: Nobody knows how to build with AI yet

#328

Post by tacker2000 »

pluc wrote: post #285
chamomeal wrote: post #167

Earlier quoted context omitted.

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 cou…

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.

I think it’s more nuanced than that.

Not every project one does will be or should be considered art or a source of joy and pride.

The boring CRUD apps that put the “bread on the table” are just that, a means to an end, they will not be your main source of pride or fulfillment. But somewhere in between there will be projects where you can put all your heart in and turn off that LLM.

Think of the countless boring weddings playlists a DJ has to do or the boring “give me the cheapest” single family homes an architect has to design.

Re: Nobody knows how to build with AI yet

#329

Post by NohatCoder »

So, is Protocollie actually any good? I don't have any means of evaluating the final product, but I feel like evaluating what ultimately stuck to the wall is a pretty important part of the tale.

How buggy is it? How long would it have taken to build something similar by hand?

Re: Nobody knows how to build with AI yet

#330

Post by Xss3 »

dustingetz wrote: post #315
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…

your problem domain is greenfield freelancing if i am reading you correctly? The tarpit of AI discussion is that everybody assumes that their local perspective is globally applicable. It is not.

This.

I work in a large corpo eco system of products across languages that talk to a mess of micro and not so micro services.

Ai tools are rarely useful out of the box in this context. Mostly because they can't fit the ecosystem into their context. I think i would need 10 agents or more for the task.

We have good documentation, but just fitting the documentation into context alongside a microservice is a tight fit. Most services would need one agent for the code (and even then it'd only fit 10% in context), and one for the docs.

Trying to use them without sufficient context, or trying to cram the right 10% into context, takes more effort than just coding the feature, and produces worse results with the worst kind of bugs, subtle ones borne from incorrect assumptions.

Post reply on HN