Live data from Hacker News

AI-written code is still your code

martiansoftware.com

51–60 of 99 posts

Re: AI-written code is still your code

#51
post #46

> It’s crystal clear that AI can be a complexity factory. > keeping software understandable to humans a first-class design goal in the age of AI. I'm not sure this is going to be a worthwhile goal for much longer. Rarely is anyone caring about the complexity and comprehensibility of the ASM that GCC or LLVM generates from higher-level C code. I think the code-generation abstraction is just moving even higher now into…

How can you scrutinize something you don't understand?

Re: AI-written code is still your code

#53
Interestingly enough, the question "do we want to support it" has been the main one (not "can we write it") in any sufficiently large and mature project for as long as I remember.

Now, becoming large is now a solved problem essentially, but that's still only maybe 10-20% of the software engineering work in the long run. I'm grateful I can delegate some grunt work to LLMs, but, essentially, the main reason why large projects slow down development has never been due to inability to write lots of code quickly.

Re: AI-written code is still your code

#54
post #34

This is why I don't use AI to write code directly but instead will use it to generate code snippets or ideas or critique, or even just use it as documentation I can talk to. By doing this I can still get the benefits of the technology including - and this is crucial - as a learning aid to improve my own skills, while not entirely outsourcing my own thinking to the machine.

This is exactly how AI should be used when coding. "Agentic" AI produces garbage code. The entire codebase should never be accessible to the context (even if parts at a time, if the agent chooses the parts). And the entire codebase should never be write accessible. Only limited scope writes, human read, and approved.

Re: AI-written code is still your code

#55
The balance sheets of the AI providers are pretty clear on this ownership thing: I shouldn't own it, NVidia should. Instead, I should pay at least once a very large amount to initially produce it. And then I should have a recurring usage-based monthly fee - for a license allowing me to say it's "my code". That's on top of hosting fees, etc.

Re: AI-written code is still your code

#56
post #2

I keep getting downvoted for saying this but I still review all of my AI generated code. I feel like I’m sufficiently sped up. Of course you can go faster if you don’t read the code at all, that’s always been true. But it seems like the ability to emit large quantities of text is already a huge leap in productivity. I don’t think these tools are good enough yet to offload all or our thinking into them.

What do you say to your boss if they ask why your colleague is producing 10-100x the kloc as you?

Re: AI-written code is still your code

#57
post #6

I'm not OK with it, but I have no choice besides maybe quitting my job. I've also tried to understand the code that AI writes, but it's often insane and untangling it would slow me down so much that it would nullify the gains in speed that AI brings. To me, either companies realize they're spending a lot more money to ship crappier code and AI becomes a niche, or we'll just stop looking at code. I don't think there's…

My company recently had to cut back our usage to effectively nothing and I get to code by hand again. I'm going to appreciate it while I can. The AI just wasn't providing enough value for us

Re: AI-written code is still your code

#59
post #14

> It’s crystal clear that AI can be a complexity factory. > I’ve been thinking a lot lately about what software would look like if we made keeping software understandable to humans a first-class design goal in the age of AI. I agree, and I've been thinking similarly. But I don't think there's anything "new" about what understandable and well-factored code should look like. It's the same principles as ever. A lot of a…

There are deterministically computable metrics for cognitive complexity and readability[0]. They’re not perfect by any means — and I suspect they’re already included in the RL process for coding evals, and have been for some time. I do think we’ll see ongoing improvement in this area though. [0] (pdf warning) https://www.sonarsource.com/docs/CognitiveComplexity.pdf

See also: Goodhart's law
Post reply on HN