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

Automatic Programming

antirez.com

Post reply on HN
Print view View original

211–220 of 257 posts

Re: Automatic Programming

#211

Post by zahlman »

bitwize wrote: post #188
zahlman wrote: post #133

Earlier quoted context omitted.

> We maybe witnessing the last generation of master software artisans like antirez. I'm told that chess is more popular than ever, despite it being decades since a human could dream of beating a top computer at it.

More relevantly, I've been seeing an explosion of (ostensibly) human-produced artwork in my SM feed, despite that Stable Diffusion and the like are supposed to bypass the need for artistic skill and make your anime waifu come to laifu with a paragraph of prompt.

Sorry, "SM"?

Re: Automatic Programming

#212

Post by CamperBob2 »

bitwize wrote: post #154
bko wrote: post #63

Earlier quoted context omitted.

I don't understand this perspective. Programmers often scoff at most other examples of intellectual property, some throwing it out all together. I remember reading Google vs Oracle where Oracle sued Google for stealing code to perform a range check, about about 9 lines long, used to check array index bounds. I guess the difference is AI companies bad? This is transformative technology creating trillions in value and…

Hot take: The Supreme Court should have sided with Oracle. APIs are a clear example of unique expression, and there is no statute exempting them specifically from copyright protection. If they are not protected by copyright, is anything really? What meaning has copyright law then?

Why is copyright law more important than anything else? AI is likely to drive the next stage of humanity's intellectual evolution, while copyright is a leaky legal abstraction that we pulled out of our asses a couple hundred years ago.

One of these is much more important than the other. If the copyright cartels insist on fighting AI, then they must lose decisively.

Re: Automatic Programming

#213

Post by bitwize »

zahlman wrote: post #211
bitwize wrote: post #188

Earlier quoted context omitted.

More relevantly, I've been seeing an explosion of (ostensibly) human-produced artwork in my SM feed, despite that Stable Diffusion and the like are supposed to bypass the need for artistic skill and make your anime waifu come to laifu with a paragraph of prompt.

Sorry, "SM"?

social media

not... not the other kind of SM

Re: Automatic Programming

#214

Post by throwdbaaway »

mejthemage wrote: post #202
rvz wrote: post #2

> I'm a programmer, and I use automatic programming. The code I generate in this way is mine. My code, my output, my production. I, and you, can be proud. Disagree. So when there is a bug / outage / error, due to "automatic programming" are you ready to be first in line to accept accountability (the LLM cannot be) when it all goes wrong in production? I do not think that would even be enough or whether this would wor…

I hope you aren't missing the point. My position is similar to the author. I WILL take responsibility for the code I push to production, and rather than input a prompt and roll the dice on the outcome, I am strategic in my prompts, ensuring the LLM has the right context each time I I voke it, some of that context being accurate descriptions of what I want built, and I am in charge of ensuring it has been properly vet…

> Many times I will erase what the LLM has written and redo it, by myself depending on the situation.

The contention here is that antirez doesn't think this is necessary anymore. 100% code gen, with the occassional "stepping in and tell the AI how to write a certain function"

Your position is more balanced and quite similar to https://mitchellh.com/writing/non-trivial-vibing

Re: Automatic Programming

#216

Post by manmal »

wenc wrote: post #206
manmal wrote: post #200

Earlier quoted context omitted.

My experience with both Opus and GPT-codex is that they both just forget to implement big chunks of specs, unless you give them the means to self-validate their spec conformance. I’m finding myself sometimes spending more time coming up with tooling to enable this, than the actual work.

The key is generating a task list from the spec. Kiro IDE (not cli) generates tasks.md automatically. This is a checklist that Opus has to check off. Try Kiro. It's just an all-round excellent spec-driven IDE. You can still use Claude Code to implement code from the spec, but Kiro is far better at generating the specs. p.s. if you don't use Kiro (though I recommend it), there’s a new way too — Yegge’s beads. After yo…

I’ve even built my own todo tool in zig, which is backed by SQLite and allows arbitrary levels of todo hierarchy. Those clankers just start ignoring tasks or checking them off with a wontfix comment the first time they hit adversity. Codex is better at this because it keeps going at hard problems. But then it compacts so many times over that it forgets the todo instructions.

Re: Automatic Programming

#217

Post by _alaya »

Yes! Hooray! Automatic Programming!

I embrace this new term.

"Vibe coding" is good for describing a certain style of coding with AI.

"Automatic programming" is what I get paid for in my 9-5, things have to work and they have to work correctly. Things I write run in real production with real money at stake. Thus, I behave like an adult and a professional.

Thank you 'antirez for introducing this language.

Re: Automatic Programming

#218

Post by ares623 »

GeoAtreides wrote: post #204
kubelsmieci wrote: post #203

Earlier quoted context omitted.

let's have another though experiment: there are two programmers. first is very talented technically, but weak at negotiations, so he earns median pay. second is average technically, but very good at negotiations, and he earns much better. is it fair? life is not fair.

Surely one easily see that the second programmer didn't take the first programmer talent (or his knowledge) and claimed it as their own...

Engineers man… of all the problems we see today, giving real power to engineers is probably a root cause of many.

Re: Automatic Programming

#219

Post by radialstub »

ares623 wrote: post #218
GeoAtreides wrote: post #204

Earlier quoted context omitted.

Surely one easily see that the second programmer didn't take the first programmer talent (or his knowledge) and claimed it as their own...

Engineers man… of all the problems we see today, giving real power to engineers is probably a root cause of many.

In China, engineers hold the most power, yet the country prospers. I don't think the problem is giving engineers power, rather a cultural thing. In china there is a general feeling of contributing towards the society, in the US everyone is trying to screw over each-other, for political or monetary reasons.

Re: Automatic Programming

#220

Post by lenkite »

slim wrote: post #198
wernsey wrote: post #173

Earlier quoted context omitted.

I disagree. Code is the expression of knowledge and can be protected by copyright. A lot of the popular licenses on GitHub (like MIT) permits you to use a piece of code on the condition that you credit the original author. If an LLM outputs code from such a project (or remixes code from several such projects) then it needs to credit the original authors or be in violation. If Disney's intellectual property can be sto…

We're not talking about the expression of knowledge. What is used in AI models is the knowledge from that expression. That code is not copied as is, instead knowledge is extracted from it and used to produce similar code. Copy right does not apply, IMHO

So you can train AI on Disney Movies to generate and sell your own disney movies because "knowledge is extracted" from it ? Betcha that won't fly in the courts. Here is "Slim Cinderella" - trained and extracted from all Disney Cinderella movies!
Post reply on HN