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

181–190 of 432 posts

Re: Nobody knows how to build with AI yet

#181

Post by bradly »

bloppe wrote: post #62
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.

An I the only one who has to constantly tell Claude and Gemini to stop making edits to my codebase because they keep messing things up and breaking the build like ten times in a row, duplicating logic everywhere, etc? I keep hearing about how impressive agents are. I wish they could automate me out of my job faster

This is way even as a paid user I stick to the browser tab llms. I am a context control freak and constantly just grabbing a new sessions and starting over. I don't try and fix a session and the incentives of a subscription vs api token payment model has inverse incentives.

Re: Nobody knows how to build with AI yet

#182

Post by bGl2YW5j »

sansseriff wrote: post #122

There's a weird insecurity I've noticed cropping up. I want to design the codebase 'my way'. I want to decide on the fundamental data structures. But there's this worry that my preferred architecture is not massively better than whatever the machine comes up with. So by insisting on 'my way' I'm robbing everyone productivity. I know most true programmers will vouch for me and my need to understand. But clients and pr…

Until an LLM or some new form of AI can manage an entire architecture itself, I say we need a middle ground. Something will always go wrong, and understanding of the system is necessary to troubleshoot.

Re: Nobody knows how to build with AI yet

#183

Post by ath3nd »

gabrieledarrigo wrote: post #169
recursive wrote: post #119

Earlier quoted context omitted.

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.

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=44598254#44602695) without telling you, let's just ignore those facts and fanboy with wide-closed about that future.

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

Re: Nobody knows how to build with AI yet

#184

Post by forrestthewoods »

Yawn. I wish HN would just ban AI skip articles until someone writes about an actual product that provides actual value to paying customers.

In fact what I really want to see is a successful product that no one realizes was built by AI vibes until after it was successful. Customers don’t give a shit how something was built.

Re: Nobody knows how to build with AI yet

#185

Post by herval »

saadatq wrote: post #177

this isn’t vibe coding. This is something completely new. I call it “flex coding.” heck I built a full app in an afternoon AND I was a good dad? > I'd wander into my office, check what Claude had built, test it real quick. If it worked, great! Commit and push. "Now build the server connection UI," I'd say, and wander back out. Made breakfast. Claude coded. Played with my son. Claude coded. Watched some TV. Claude cod…

careful, Claude might soon start complaining you're not pulling your weight and refuse to work

Re: Nobody knows how to build with AI yet

#186

Post by mmcconnell1618 »

ivanjermakov wrote: post #32
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…

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

English and other languages come with lots of ambiguity and assumptions. A significant benefit of programming languages is they have explicit rules for how they will be converted into a running program. An LLM can take many paths from the same starting prompt and deliver vastly different output.

Re: Nobody knows how to build with AI yet

#187

Post by thegrim33 »

I know it's an analogy that's probably been done to death already, but it truly feels like Bitcoin 2.0.

Back in the Bitcoin hype days, there were new posts here every single day about the latest and greatest Bitcoin thing. Everyone was using it. It was going to take over the world. Remember all the people on this very site that sincerely thought fiat currency was going away and we'd be doing all of our transactions with Bitcoin? How'd that work out?

It feels exactly the same. Now the big claims are that coding jobs are going away, or if you at least don't use it you'll be left behind. People are posting AI stories every day. Everyone is using it. People say it's going to transform the industry.

Back then there was greater motivation to evangelize Bitcoin, as you could get rich by convincing people to buy in, and it's just to a lesser degree now. People who work for AI companies (like the author), posting AI stuff, trying to drum up more people to give them views/clicks, buy their products.

And of course you'll have people replying to this trying to make the case for why AI coding is already a thing, when in reality those posts are once again going to be carbon copies of similar comments from the Bitcoin days "hey, you're wrong, I bought pizza with Bitcoin last night, it's already taking over, bud!"

Re: Nobody knows how to build with AI yet

#189

Post by simonw »

codingdave wrote: post #52
logicchains wrote: post #41

Earlier quoted context omitted.

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?

If you tell it to reinvent the wheel, it will.

If you tell it to use existing libraries (and they are in its training data) it will do that instead.

If you tell it about libraries it hasn't encountered before it can use those instead.

Re: Nobody knows how to build with AI yet

#190

Post by vishvananda »

Benjammer wrote: post #173
vishvananda wrote: post #156

Earlier quoted context omitted.

I'm really baffled why the coding interfaces have not implemented a locking feature for some code. It seems like an obvious feature to be able to select a section of your code and tell the agent not to modify it. This could remove a whole class of problems where the agent tries to change tests to match the code or removes key functionality. One could even imagine going a step further and having a confidence level ass…

Why are engineers so obstinate about this stuff? You really need a GUI built for you in order to do this? You can't take the time to just type up this instruction to the LLM? Do you realize that's possible? You can just write instructions "Don't modify XYZ.ts file under any circumstances". Not to mention all the tools have simple hotkeys to dismiss changes for an entire file with the press of a button if you really w…

I am by no means an AI skeptic. It is possible to encode all sorts of things into instructions, but I don’t think the future of programming is every individual constructing and managing artisan prompts. There are surely some new paradigms to be discovered here. A code locking interface seems like an interesting one to explore. I’m sure there are others.
Post reply on HN