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

241–250 of 257 posts

Re: Automatic Programming

#241

Post by deterministic »

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.…

How detailed are the specs? Is it basically pseudo code? Can you please give an example of a spec point?

Re: Automatic Programming

#242

Post by jryan49 »

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

Then why was Claude code generating exact copies of code files all with the copyrights intact last week when I used it?

Re: Automatic Programming

#243

Post by lenkite »

its_ubuntu wrote: post #234
lenkite wrote: post #220

Earlier quoted context omitted.

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!

[dead]

Sure, you can do it illegally - by breaking the law and recognizing that you need to be a fugitive. You can give up civilization and live in the wilderness. People can do whatever they want on their 10 year old Dell as long as they don't sell/distribute products made from other people's true efforts.

Re: Automatic Programming

#244

Post by ouchiepouchie »

its_ubuntu wrote: post #233
heavyset_go wrote: post #209

Earlier quoted context omitted.

Licenses mean nothing if AI training on your data is fair use, which courts have yet to determine. You can have a license that says "NO AI TRAINING EVER" in no uncertain terms and it would mean absolutely nothing because fair use isn't dictated by licenses.

[dead]

Which God are you talking about, and how do you believe they have communicated this?

Re: Automatic Programming

#245

Post by airbreather »

Nothing has changed, it is just now, more than ever, specification is everything.

It is just that for some decades now it was possible to get away with poor or lacking specification, by continually incrementing by sprints, or pivoting, or whatever.

But, back in the day when systems analysts were still a person with very particular skills that might never code, specification was everything.

And now, the wheel turns, and the importance of good specification appears to be the defining factor once again, all of a sudden.

Re: Automatic Programming

#246

Post by airbreather »

manmal wrote: post #79
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.…

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…

Most people do not believe it is possible to fully specify software before writing it, until they are forced to.

Having part of my background in Functional Safety, I have seen it done many times, and it can most definitely be done.

It is just it can't be done in the sort of time frames that people who do not specify before coding, are used to.

But, if you can't afford to move fast and break tings, because it is an airplane, or train signaling system, or complicated elevator system with multiple cars in the same shaft, then you generally write no code until you know exactly what you want the code to do (and more importantly, not do).

Re: Automatic Programming

#247

Post by airbreather »

catdog wrote: post #71
user3939382 wrote: post #44

Earlier quoted context omitted.

I spent my career building software for executives that wanted to know exactly what they were going to get and when because they have budgets and deadlines i.e. the real world. Mostly I’ve seen agile as, let’s do the same thing 3x we could have done once if we spent time on specs. The key phrase here is “requirements analysis” and if you’re not good at it either your software sucks or you’re going to iterate needless…

> The key phrase here is “requirements analysis” and if you’re not good at it either your software sucks or you’re going to iterate needlessly and waste massive time including on bad architecture. You don’t iterate the foundation of a house. This depends heavily on the kind of problem you are trying to solve. In a lot of cases requirements are not fixed but evolve over time, either reacting to changes in the real wor…

The key first step here is "Problem Identification" - the number of times I have seen where it is part way through a development, and only then it starts to become obvious that even if the specifications were good, they were not solving the right problem.

Users have a habit of describing their problem as the solution they think they would like to have, often being disastrously far from the actual need.

Re: Automatic Programming

#248

Post by airbreather »

motoboi wrote: post #93

We maybe witnessing the last generation of master software artisans like antirez. This is beautiful to see, their mastery harnessing the power of the intelligent machine tools to design, understand and build. This is like seeing a master of image & light like michelangelo receiving a camera, photoshop and a printer. It's an exponential elevation of the art. But to become a master like michelangelo one had to dedicate…

The true art is in the architecture, which is the bit humans still generally control, not the tiny details.

Unless you would rather be a calligrapher than a novelist.

Re: Automatic Programming

#249

Post by theshrike79 »

manmal wrote: post #200
wenc wrote: post #135

Earlier quoted context omitted.

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.

I just use beads or Github issues. Plan/spec first, split it into issues.

Then reset context and implement each task one by one. Nothing gets forgotten.

Re: Automatic Programming

#250

Post by theshrike79 »

motoboi wrote: post #93

We maybe witnessing the last generation of master software artisans like antirez. This is beautiful to see, their mastery harnessing the power of the intelligent machine tools to design, understand and build. This is like seeing a master of image & light like michelangelo receiving a camera, photoshop and a printer. It's an exponential elevation of the art. But to become a master like michelangelo one had to dedicate…

I don't see anyone lamenting the generation who single-handedly built games in machine code for the early home computers. No art was lost, we just evolved and started using more advanced languages that didn't require as much dedication to work in.
Post reply on HN