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

AI coding

geohot.github.io

Post reply on HN
Print view View original

221–230 of 299 posts

Re: AI coding

#221

Post by paool »

mihaic wrote: post #124
matt3D wrote: post #70

This is a more extreme example of the general hacker news group think about AI. Geohot is easily a 99.999 percentile developer, and yet he can’t seem to reconcile that the other 99.999 percent are doing something much more basic than he can ever comprehend. It’s some kind of expert paradox, if everyone was as smart and capable as the experts, then they wouldn’t be experts. I have come across many developers that beha…

[flagged]

In the early days of Bitcoin, I was able to send transactions programmatically. Built my own js library using json-rpc to communicate with a node.

Geohot live streamed himself broadcasting a transaction from scratch.

For that I respect his level of knowledge. Plus he built comma which is a product I use almost everyday.

Re: AI coding

#222

Post by platevoltage »

tom_m wrote: post #201
bdcravens wrote: post #25

I'm almost 50, and have been writing code professionally since the late 90s. I can pretty much see projects in my head, and know exactly what to build. I also get paid pretty well for what I do. You'd think I'd be the prototype for anti-AI. I'm not. I can build anything, but often struggle with getting bogged down with all the basic work. I love AI for speed running through all the boring stuff and getting to the goo…

Exactly. If you know how the whole thing works end to end, AI makes you incredibly dangerous. Anyone who specializes or never really learned how everything works is at a huge disadvantage. However. There's also good news. AI is also an amazing tool for learning. So what I see AI doing is simply separating people who want to put effort forth and those who don't.

I agree. Having AI write your entire application is equivalent to having it write a song for your band, or even generate audio so you don't have to do record it yourself.

If you aren't talented enough to write or record your own music, you aren't really a musician.

If you have a quick question about music theory and you want a quick answer, AI can be a benefit.

Re: AI coding

#223

Post by pydry »

bdcravens wrote: post #67
pydry wrote: post #55

Earlier quoted context omitted.

>AI changes the job to be a constant struggle with hard problems I find this hilarious. From what I've seen watching people do it, it changes the job from deep thought and figuring out a good design to pulling a lever on a slot machine and hoping something good pops out. The studies that show diminished critical thinking have matched what i saw anecdotally pairing with people who vibe coded. It replaced deep critical…

Which was my original point. Not that the outcome is shit. So much of what we write is absolutely low-skill and low-impact, but necessary and labor-intensive. Most of it is so basic and boilerplate you really can't look at it and know if it was machine- or human-generated. Why shouldn't that work get cranked out in seconds instead of hours? Then we can do the actual work we're paid to do. To pair this with the commen…

>So much of what we write is absolutely low-skill and low-impact, but necessary and labor-intensive.

Ive never found this to be true once in my career.

I know a lot of devs who looked down on CRUD or whatever it was they were doing and produced boilerplate slop though.

Code isnt like pottery. There arent "artisanal" devs who produce lovely code for people to look at like it's a beautiful vase. Good code that is hooked into the right product-market fit can reach millions of people if it works well.

The world was replete with shitty code before AI and mostly it either got tossed away or it incurred epic and unnecessary maintenance costs because it actually did something useful. Nothing has changed on that front except the tsunami of shit got bigger.

Re: AI coding

#224

Post by platevoltage »

st-keller wrote: post #147
bdcravens wrote: post #25

I'm almost 50, and have been writing code professionally since the late 90s. I can pretty much see projects in my head, and know exactly what to build. I also get paid pretty well for what I do. You'd think I'd be the prototype for anti-AI. I'm not. I can build anything, but often struggle with getting bogged down with all the basic work. I love AI for speed running through all the boring stuff and getting to the goo…

That‘s exactly why i like AI too. I even let them play roles like „junior dev“, „product owner“ or „devops engineer“ and orchestrate them, to play together as a team - with guidance from me (usually the „solution architect“ or „investor“)! This „team“ achieves in weeks what we usually needed months for - for 2.40€/h*role!

This sounds a bit like creating a Humanoid robot to do dishes instead of a machine specifically designed to do dishes.

Re: AI coding

#225

Post by jrm4 »

Again, can't help but wonder when we might improve this conversation by more strongly defining "what kind of programming."

It's just like "Are robots GOOD or BAD at building things?"

WHAT THINGS?

Re: AI coding

#227

Post by efitz »

FeepingCreature wrote: post #74
onion2k wrote: post #48

Earlier quoted context omitted.

I love AI for speed running through all the boring stuff and getting to the good parts. In some cases, especially with the more senior devs in my org, fear of the good parts is why they're against AI. Devs often want the inherent safety of the boring, easy stuff for a while. AI changes the job to be a constant struggle with hard problems. That isn't necessarily a good thing. If you're actually senior by virtue of tim…

That makes me think of https://store.steampowered.com/app/2262930/Bombe/ which is a version of Minesweeper where instead of clicking on squares you define (parametric!) rules that propagate information around the board automatically. Your own rules skip all the easy parts for you. As a result, every challenge you get is by definition a problem that you've never considered before. It's fun, but also exhausting.

I just tried that game and it looks very interesting but the interface is cryptic.

Re: AI coding

#228

Post by btown »

> AI workflows are, in practice, highly non-deterministic. While different versions of a compiler might give different outputs, they all promise to obey the spec of the language, and if they don’t, there’s a bug in the compiler. English has no similar spec.

AI coding shines when this is a good thing. For instance, say you have to adapt the results of one under-documented API into another. Coding agents like Claude Code can write a prototype, get the real-world results of that API, investigate the contents, write code that tries to adapt, test the results, rewrite that code, test again, rewrite again, test again, ad nauseam.

There are absolutely problem domains where this kind of iterative adaptation is slower than bespoke coding, where you already have the abstractions such that every line you write is a business-level decision that builds on years of your experience.

Arguably, Geohot's low-level work on GPU-adjacent acceleration is a "wild west" where his intuition outstrips the value of experimentation. His advice is likely sound for him. If he's looking for a compiler for the highly detailed specifications that pop into his head, AI may not help him.

But for many, many use cases, the analogy is not a compiler; it is a talented junior developer who excels at perseverance, curiosity, commenting, and TDD. They will get stuck at times. They will create things that do not match the specification, and need to be code-reviewed like a hawk. But by and large, if the time-determining factor is not code review but tedious experimentation, they can provide tremendous leverage.

Re: AI coding

#229

Post by platevoltage »

neurostimulant wrote: post #153
hereme888 wrote: post #95

I'm a 100% vibe-coder. AI/CS is not my field. I've made plenty of neat apps that are useful to me. Don't ask me how they work; they just do. Sure the engineering may be abysmal, but it's good enough to work. It only takes basic english to produce these results, plus complaining to the AI agent that "The GUI is ugly and overcrowded. Make it look better, and dark mode." Want specs? "include a specs.md" This isn't a 20%…

I think it's like CMS and page builders enabling people to build their own websites without html and server knowledge. They're not making web developers disappear, instead there are more web developers now because those some of those people would eventually outgrow their page builders and need to hire web developers.

This is the optimistic view that I see around. I go back and forth. I've had some work that was the result of "vibe coders" hitting a wall with its capabilities.

Re: AI coding

#230

Post by andrewchambers »

Kind of surprised by this take - I use openpilot often and also use claude code.

I kind of consider them the same thing. Openpilot can drive really well on highways for hours on end when nothing interesting is happening. Claude code can do straight forward refactors, write boilerplate, do scaffolding, do automated git bisects with no input from me.

Neither one is a substitute for the 'driver'. Claude code is like the level 2 self driving of programming.

Post reply on HN