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

191–200 of 257 posts

Re: Automatic Programming

#191

Post by orochimaaru »

dugmartin wrote: post #21

I have 30+ years of industry experience and I've been leaning heavily into spec driven development at work and it is a game changer. I love programming and now I get to program at one level higher: the spec. I spend hours on a spec, working with Claude Code to first generate and iterate on all the requirements, going over the requirements using self-reviews in Claude first using Opus 4.5 and then CoPilot using GPT-5.…

Agile isn’t against spec writing. Specs can be a task in your story and so can automated tests. Both can be deliverables in your acceptance criteria. But that’s not how it went - because the human nature is to look for least effort.

Which AI, least effort is the specs so that’s the “greatest thing to do” again.

Re: Automatic Programming

#192

Post by jdjdjssh »

dugmartin wrote: post #21

I have 30+ years of industry experience and I've been leaning heavily into spec driven development at work and it is a game changer. I love programming and now I get to program at one level higher: the spec. I spend hours on a spec, working with Claude Code to first generate and iterate on all the requirements, going over the requirements using self-reviews in Claude first using Opus 4.5 and then CoPilot using GPT-5.…

[dead]

Re: Automatic Programming

#193

Post by dang »

jpnc wrote: post #27
dang wrote: post #194

[stub for offtopicness]

How does it feel to see all your programming heroes turn into Linkedin-style influencers?

Please don't cross into personal attack, no matter how much you dislike an article.

You may not owe programming heroes or Linkedin inluencers better, but you owe this community better if you're participating in it.

https://news.ycombinator.com/newsguidelines.html

Re: Automatic Programming

#195

Post by sneak »

heavyset_go wrote: post #130
sneak wrote: post #87

Earlier quoted context omitted.

Copyright infringement is a tort. “Illegal” is almost always used to refer to breaking of criminal law. This seems like intentionally conflating them to imply that appropriating code for model training is a criminal offense, when, even in the most anti-AI, pro-IP view, it is plainly not.

https://www.justice.gov/archives/jm/criminal-resource-manual...

> There are four essential elements to a charge of criminal copyright infringement. In order to sustain a conviction under section 506(a), the government must demonstrate: (1) that a valid copyright; (2) was infringed by the defendant; (3) willfully; and (4) for purposes of commercial advantage or private financial gain.

I think it’s very much an open debate if training a model on publicly available data counts as infringement or not.

Re: Automatic Programming

#196

Post by logicprog »

GeoAtreides wrote: post #190
logicprog wrote: post #169

Earlier quoted context omitted.

I draw from this that no-one should be subject to those rules, and we should try to use the AI companies as a wedge to widen that crack. Instead, most people people who claim that their objection is really only consistency, not love for IP spend their time trying to tighten the definitions of fair use, widen the definitions of derivative works, and in general make IP even stronger, which will effect far more than jus…

oh hey, let's have a thought experiment in this world with no IP rules suppose I write a webnovel that I publish for free on the net, and I solicit donations. Kinda like what's happening today anyway. Now suppose I'm not good at marketing, but this other guy is. He takes my webnovel, changes some names, and publishes it online under his name. He is good at social media and marketing, and so makes a killing from donat…

There are also unfair situations that can happen, equally as often, if IP does exist, and likewise, in those situations, those with more money, influence, or charisma will win out.

Also, the idea that that situation is unfair relies entirely on the idea that we own our ideas and have a right to secure (future, hypothetical) profit from them. So you're essentially begging the question.

You're also relying on a premise that, when drawn out, seems fundamentally absurd to me: that you should own not just the money you earn, but the rights to any money you might earn in the future, had someone not done something that caused unrelated others to never have paid you. If you extend that logic, any kind of competition is wrong!

Re: Automatic Programming

#197

Post by amelius »

tonyedgecombe wrote: post #40
reidrac wrote: post #20

> Pre-training is, actually, our collective gift that allows many individuals to do things they could otherwise never do, like if we are now linked in a collective mind, in a certain way. Is not a gift if it was stolen. Anyway, in my opinion the code that was generated by the LLM is yours as long as you're responsible for it. When I look at a PR I'm reading the output of a person, independently of the tools that pers…

>Is not a gift if it was stolen. Yeah, I had a visceral reaction to that statement.

Yet nobody is changing their licenses to exclude AI use. So I assume they are OK with it.

Re: Automatic Programming

#198

Post by slim »

wernsey wrote: post #173
slim wrote: post #36

Earlier quoted context omitted.

It is knowledge, it can't be stolen. It is stolen only in the sense of someone gatekeeping knowledge. Which is as a practice, the least we can say, dubious. because is math stolen ? if you stole math to build your knowledge on top of it, you own nothing and can claim to have been stolen yourself

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. Copyright does not apply, IMHO

Re: Automatic Programming

#199

Post by manmal »

nl wrote: post #89
manmal wrote: post #79

Earlier quoted context omitted.

My experience is that such one-shotted projects never survive the collision with reality. Even with extremely detailed specs, the end result will not be what people had in mind, because human minds cannot fully anticipate the complexity of software, and all the edge cases it needs to handle. "Oh, I didn't think that this scheduled alarm is super annoying, I'd actually expect this other alarm to supersede it. It's gre…

I think there's a difference between people getting a system a d realising it isn't actually what they wanted and "never survive collision with reality". They survive by being modified and I don't think that invalidates the process that got them in front of people faster than would otherwise have been possible. This isn't a defence of waterfall though. It's really about increasing the pace of agile and the size of th…

I think I agree with what you’re saying? But that’s not the waterfall approach GP pitched.

Re: Automatic Programming

#200

Post by manmal »

wenc wrote: post #135
manmal wrote: post #79

Earlier quoted context omitted.

My experience is that such one-shotted projects never survive the collision with reality. Even with extremely detailed specs, the end result will not be what people had in mind, because human minds cannot fully anticipate the complexity of software, and all the edge cases it needs to handle. "Oh, I didn't think that this scheduled alarm is super annoying, I'd actually expect this other alarm to supersede it. It's gre…

I've been doing spec-driven development for the past 2 months, and it's been a game changer (especially with Opus 4.5). Writing a spec is akin to "working backwards" (or future backwards thinking, if you like) -- this is the outcome I want, how do I get there? The process of writing the spec actually exposes the edge cases I didn't think of. It's very much in the same vein as "writing as a tool of thought". Just gett…

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.
Post reply on HN