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

Scaling long-running autonomous coding

cursor.com

Post reply on HN
Print view View original

31–40 of 203 posts

Re: Scaling long-running autonomous coding

#31

Post by blamestross »

jphelan wrote: post #15

This looks like extremely brittle code to my eyes. Look at https://github.com/wilsonzlin/fastrender/blob/main/crates/fa... What is `FrameState::render_placeholder`? ``` pub fn render_placeholder(&self, frame_id: FrameId) -> Result { let (width, height) = self.viewport_css; let len = (width as usize) .checked_mul(height as usize) .and_then(|px| px.checked_mul(4)) .ok_or_else(|| "viewport size overflow".to_string())?;…

I suppose brittle code is fine if you have cursor to update and fix it. Ideal really, keeps you dependent.

Re: Scaling long-running autonomous coding

#32

Post by icedchai »

tired_and_awake wrote: post #28

The moment all code is interacted with through agents I cease to care about code quality. The only thing that matters is the quality of the product, cost of maintenance etc. exactly the thing we measure software development orgs against. It could be handy to have these projects deployed to demonstrate their utility and efficacy? Looking at PRs of agents feels a wrong headed, like who cares if agents code is hard to r…

This is how we wound up with non-technical "engineering managers." Looks good to me.

Re: Scaling long-running autonomous coding

#33

Post by matthewfcarlson »

It’s fascinating that many of the issues they faced I’ve seen in human software engineering teams.

Things like integration creating bottlenecks or a lack of consistent top down direction leading to small risk adverse changes instead of bold redesigns. All things I’ve seen before.

Re: Scaling long-running autonomous coding

#34

Post by visarga »

tired_and_awake wrote: post #28

The moment all code is interacted with through agents I cease to care about code quality. The only thing that matters is the quality of the product, cost of maintenance etc. exactly the thing we measure software development orgs against. It could be handy to have these projects deployed to demonstrate their utility and efficacy? Looking at PRs of agents feels a wrong headed, like who cares if agents code is hard to r…

> Looking at PRs of agents feels a wrong headed

It would be walking the motorcycle.

Re: Scaling long-running autonomous coding

#35

Post by mkoubaa »

cheevly wrote: post #9
simonw wrote: post #3

"To test this system, we pointed it at an ambitious goal: building a web browser from scratch." I shared my LLM predictions last week, and one of them was that by 2029 "Someone will build a new browser using mainly AI-assisted coding and it won’t even be a surprise" https://simonwillison.net/2026/Jan/8/llm-predictions-for-202... and https://www.youtube.com/watch?v=lVDhQMiAbR8&t=3913s This project from Cursor is the s…

2029? I have no idea why you would think this is so far off. More like Q2 2026.

Yeah if you let them index chromium I'm sure it could do it next week. It just won't be original or interesting.

Re: Scaling long-running autonomous coding

#36

Post by sashank_1509 »

embedding-shape wrote: post #26
micimize wrote: post #25

> While it might seem like a simple screenshot, building a browser from scratch is extremely difficult. > Another experiment was doing an in-place migration of Solid to React in the Cursor codebase. It took over 3 weeks with +266K/-193K edits. As we've started to test the changes, we do believe it's possible to merge this change. In my view, this post does not go into sufficient detail or nuance to warrant any seriou…

> it's a mountain of inscrutable agent output that manages to compile But is this actually true? They don't say that as far as I can tell, and it also doesn't compile for me nor their own CI it seems.

Oh it doesn’t compile? that’s very revealing

Re: Scaling long-running autonomous coding

#37

Post by 2001zhaozhao »

matthewfcarlson wrote: post #33

It’s fascinating that many of the issues they faced I’ve seen in human software engineering teams. Things like integration creating bottlenecks or a lack of consistent top down direction leading to small risk adverse changes instead of bold redesigns. All things I’ve seen before.

At least the AI teams aren't politically competing against each other unlike human teams.

(Or are they?)

Re: Scaling long-running autonomous coding

#38

Post by micimize »

embedding-shape wrote: post #26
micimize wrote: post #25

> While it might seem like a simple screenshot, building a browser from scratch is extremely difficult. > Another experiment was doing an in-place migration of Solid to React in the Cursor codebase. It took over 3 weeks with +266K/-193K edits. As we've started to test the changes, we do believe it's possible to merge this change. In my view, this post does not go into sufficient detail or nuance to warrant any seriou…

> it's a mountain of inscrutable agent output that manages to compile But is this actually true? They don't say that as far as I can tell, and it also doesn't compile for me nor their own CI it seems.

Hah I don't know actually! I was assuming it must if they were able to get that screenshot video.

Re: Scaling long-running autonomous coding

#39

Post by mkoubaa »

risyachka wrote: post #30
trjordan wrote: post #8

This is going to sound sarcastic, but I mean this fully: why haven't they merged that PR. The implied future here is _unreal cool_. Swarms of coding agents that can build anything, with little oversight. Long-running projects that converge on high-quality, complex projects. But the examples feel thin. Web browsers, Excel, and Windows 7 exist, and they specifically exist in the LLM's training sets. The closest to real…

>> why haven't they merged that PR. because it is absolutely impossible to review that code and there is gazillion issues there. The only way it can get merged is YOLO and then fix issues for months in prod which kinda defeats the purpose and brings gains close to zero.

On the other hand, finding fixing issues for months is still training data

Re: Scaling long-running autonomous coding

#40

Post by mkoubaa »

galaxyLogic wrote: post #23
dist-epoch wrote: post #11

Earlier quoted context omitted.

Pretty much everything exists in the training sets. All non-research software is just a mishmash of various standard modules and algorithms.

Not everything, only code-bases of existing (open-source?) applications. But what would be the point of re-creating existing applications? It would be useful if you can produce a better version of those applications. But the point in this experiment was to produce something "from scratch" I think. Impressive yes, but is it useful? A more practically useful task would be for Mozilla Foundation and others to ask AI to…

You have to be careful which codebase to try this on. I have a feeling if someone unleashed agents on the Linux kernel to fix bugs it'd lead to a ban on agents there
Post reply on HN