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

Maccarone: AI-managed code blocks in Python

github.com

Post reply on HN
Print view View original

21–30 of 75 posts

Re: Maccarone: AI-managed code blocks in Python

#21

Post by orf »

verdverm wrote: post #16
orf wrote: post #7

Earlier quoted context omitted.

How would not having the source code be present/pre-generated, and thus needing to generate it at runtime, be an example of a decorator having no runtime effects?

OP has to be doing some parsing somewhere, so you just switch to seeking decorators rather than magic comments. It's still before the code reaches the interpreter. The potential issue I see here is that comments are valid anywhere while decorators may not be, but the parser is hopefully resilient to that. You could see a multi-phase LLM that uses the interpreter to ensure the code runs / works as expected

It literally just adds the code to the file between the comments. There’s nothing more magic than copy+paste and no runtime component.

It’s completely different from a decorator that generates code at runtime? As in, when the code runs?

Re: Maccarone: AI-managed code blocks in Python

#23

Post by groby_b »

biesnecker wrote: post #19
Nullabillity wrote: post #13

"Hallucination isn't a real problem, people will always scrutinize the generated code!" Sigh...

Thorough code review is why we as an industry stopped shipping bugs.

We, as an industry, didn't stop shipping bugs. (Small example: https://github.com/CVEProject/cvelistV5/releases)

And that thorough code review prevents bugs is, at best, a debatable assertion. See e.g. https://www.microsoft.com/en-us/research/publication/code-re...

It finds _some_ bugs. CI/CD, and a massive investment in automated testing has probably had the largest impact in moving software quality forward. (See e.g. "Accelerate", Forsgren, Humble & Kim)

Code review is an excellent tool to socialize knowledge and train up more junior engineers, but in terms of preventing bugs, it's low-value.

Re: Maccarone: AI-managed code blocks in Python

#24

Post by isaacremuant »

smrtinsert wrote: post #17

Not sure I see the benefit over standard ai integration into an editor, what am I missing?

I think they're going for some sort of high level semantic description as a workflow concept guide you instead of using AI at each individual step.

I'd much rather focus on teaching people how to think about tests and what they want to do and, when they're stuck on syntax or patterns, make sure they're thinking enough about the problem so that they know why they take the decisions they do. They can then use a search engine or AI to cover a specific technical gap.

Implenting or writing code is rarely the bottleneck for software development after enough experience so something like this doesn't seem useful for me but it's definitely cool to see people trying to integrate new technologies in different ways.

Re: Maccarone: AI-managed code blocks in Python

#25

Post by aradox66 »

groby_b wrote: post #23
biesnecker wrote: post #19

Earlier quoted context omitted.

Thorough code review is why we as an industry stopped shipping bugs.

We, as an industry, didn't stop shipping bugs. (Small example: https://github.com/CVEProject/cvelistV5/releases ) And that thorough code review prevents bugs is, at best, a debatable assertion. See e.g. https://www.microsoft.com/en-us/research/publication/code-re... It finds _some_ bugs. CI/CD, and a massive investment in automated testing has probably had the largest impact in moving software quality forward. (See e…

The parent comment is sarcastic

Re: Maccarone: AI-managed code blocks in Python

#26

Post by groby_b »

aradox66 wrote: post #25
groby_b wrote: post #23

Earlier quoted context omitted.

We, as an industry, didn't stop shipping bugs. (Small example: https://github.com/CVEProject/cvelistV5/releases ) And that thorough code review prevents bugs is, at best, a debatable assertion. See e.g. https://www.microsoft.com/en-us/research/publication/code-re... It finds _some_ bugs. CI/CD, and a massive investment in automated testing has probably had the largest impact in moving software quality forward. (See e…

The parent comment is sarcastic

Maybe. I can't read OPs mind, and it's a common enough trope throughout the industry that I figured adding some evidence could be useful.

Re: Maccarone: AI-managed code blocks in Python

#28

Post by silverthorn »

Nullabillity wrote: post #13

"Hallucination isn't a real problem, people will always scrutinize the generated code!" Sigh...

Ha, I just want to clarify that the quoted text isn't actually from the README or something like that, I'm not quite that crazy.

But no real argument with the concern. An LLM will generate bugs, and that may be a reason this kind of thing never makes sense in practice (isn't that an argument against copilot, too, though?).

Post reply on HN