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

51–60 of 432 posts

Re: Nobody knows how to build with AI yet

#51

Post by lpa22 »

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…

This is exactly what makes me excited as well. It really does replace the tedious parts of coding I’ve done thousands of times at this point.

Re: Nobody knows how to build with AI yet

#52

Post by codingdave »

logicchains wrote: post #41
djeastm wrote: post #19

Earlier quoted context omitted.

Would that application not exist in the training data already?

The are around three Golang HTTP2.0 servers on Github, but it wasn't just regurgitating the application from memory, as if it was then it would have been mostly correct first try, and it wouldn't have needed to spend 80%+ of the development time in a code-compile-test cycle of fixing bugs identified by integration tests and spec conformance tests.

So you are saying that LLMs have no capacity to re-use existing work, and will just burn hours and money re-inventing wheels?

Re: Nobody knows how to build with AI yet

#54

Post by ModernMech »

aprilthird2021 wrote: post #5

Eh, idk. First of all, the article is really wordy to say very few things. That just frustrated me a bit. Second of all, it's easy to fart out some program in a few days vibe coding. How will that fare as more and more features need to be added on? We all used to say "Dropbox that's just FTP wrapped in a nice UI anyone can make that". This protocollie project seems to be a documentation viewer / postman for MCP. Whic…

  You prompt. You go live your life. You come back to ten thousand lines of code. You spend 5 minutes reading. One sentence of feedback. Another ten thousand lines appear while you're making lunch.
Yeah, it strikes me the author writes prose the same way they're generating code. 20k lines? That's enough code for a whole compiler or an operating system kernel. I'd love to see what those 20k lines actually do -- notably, in these articles about AI, people tend to not link the actual code when they easily could, which is curious. I mean, my macro expander can also write 20k lines of code while I eat lunch, but no one is pretending it's sentient and about to replace devs.

Re: Nobody knows how to build with AI yet

#55

Post by aDyslecticCrow »

clickety_clack wrote: post #36
ivanjermakov wrote: post #32

Earlier quoted context omitted.

> Search has just become Chat I think chat-like LLM interfacing is not the most efficient way. There has to be a smarter way.

There’s an efficient way to serve the results, and there’s an efficient way for a human to consume them, and I find LLMs to be much more efficient in terms of cognitive work done to explore and understand something than a google search. The next thing will have to beat that level of personal mental effort, and I can’t imagine what that next step would look like yet.

I find a well-written human article or guide to be far more efficient when it exists. But if AI rehash them... then the market for those may disappear, and in the process, the AI won't be very good either without the source to summarise.

Re: Nobody knows how to build with AI yet

#56

Post by oblio »

mnky9800n wrote: post #49
lordnacho wrote: post #33

Earlier quoted context omitted.

But you also can't not swim with the tide. If you drove a horse-buggy 100 years ago, it was probably worth your while to keep your eye on whether motor-cars went anywhere. I was super skeptical about a year ago. Copilot was making nice predictions, that was it. This agent stuff is truly impressive.

I think the agent stuff is impressive because we are giving the AI scaffold and tools and things to do. And that is why it is impressive because it has some directive. But it is obvious if you don't give it good directives it doesn't know what to do. So for me, I think a lot of jobs will be making agents do things, but a lot won't. i think its really strange that people are all so against all this stuff. it's cool ne…

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.

Re: Nobody knows how to build with AI yet

#57

Post by hmmokidk »

jayd16 wrote: post #44
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…

Unlike peak google, this reduces signal to noise and obfuscates the source data its pulling against.

Creation of source data has been disincentivized

Re: Nobody knows how to build with AI yet

#58

Post by brabel »

Quitschquat wrote: post #35
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…

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

I was a bit wary of trusting the AI summaries Google has been including in search results… but after a few checks it seems like it’s not crap at all, it’s pretty good!

Re: Nobody knows how to build with AI yet

#59

Post by miltonlost »

rafaelmn wrote: post #43
lordnacho wrote: post #33

Earlier quoted context omitted.

But you also can't not swim with the tide. If you drove a horse-buggy 100 years ago, it was probably worth your while to keep your eye on whether motor-cars went anywhere. I was super skeptical about a year ago. Copilot was making nice predictions, that was it. This agent stuff is truly impressive.

More like people telling us there will be no more professional drivers on the road in 5-10 years 10 years ago. Agents are like lane assist, not even up to the current self driving levels.

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

Re: Nobody knows how to build with AI yet

#60

Post by sbalough »

logicchains wrote: post #37
karel-3d wrote: post #24

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…

>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. It suggests you've had very positive life experiences, that you trust human developers so much more than computers.

I don’t think that was his argument. It would be one thing if we reach a point where humans trust a higher AI intelligence to create/keep software systems predictably meeting requirements. We aren’t there yet. So, it’s important to make sure any AI code is reviewed and approved by humans.
Post reply on HN