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

151–160 of 203 posts

Re: Scaling long-running autonomous coding

#151

Post by thesz »

torginus wrote: post #89
xmprt wrote: post #12

Earlier quoted context omitted.

You're either overestimating the capabilities of current AI models or underestimating the complexity of building a web browser. There are tons of tiny edge cases and standards to comply with where implementing one standard will break 3 others if not done carefully. AI can't do that right now.

Even if AI will not achieve the ability to perform at this level on its own, it clearly is going to be an enormous force multiplier, allowing highly skilled devs to tackle huge projects more or less on their own.

Skilled devs compress, not generate (expand).

https://www.youtube.com/watch?v=8kUQWuK1L4w

The "discoverer" of APL tried to express as many problems as he could with his notation. First he found that notation expands and after some more expansion he found that it began shrinking.

The same goes to Forth, which provides means for a Sequitur-compressed [1] representation of a program.

[1] https://en.wikipedia.org/wiki/Sequitur_algorithm

Myself, I always strive to delete some code or replace some code with shorter version. First, to better understand it, second, to return back and read less.

Re: Scaling long-running autonomous coding

#153

Post by cube00 »

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…

On Jan 1 2026

> Given how badly my 2025 predictions aged I'm probably going to sit that one out! [1]

Seven days later you appear on the same podcast you appeared on in 2025 to share your LLM predictions for 2026.

What changed?

[1]: https://news.ycombinator.com/item?id=46450269

Re: Scaling long-running autonomous coding

#154

Post by simonw »

jcfrei wrote: post #135
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…

Surely a smart implementation would just find the chromium source on github, do some cosmetic rewrites and strip out all none-essential features?

You'd be able to see it doing that by looking at the transcript. You could then tell it not to!

Re: Scaling long-running autonomous coding

#155

Post by marcellus23 »

cube00 wrote: post #153
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…

On Jan 1 2026 > Given how badly my 2025 predictions aged I'm probably going to sit that one out! [1] Seven days later you appear on the same podcast you appeared on in 2025 to share your LLM predictions for 2026. What changed? [1]: https://news.ycombinator.com/item?id=46450269

He changed his mind? The comment you're citing seems partly tongue-in-cheek anyway, but even if it wasn't, how is this some kind of gotcha?

Re: Scaling long-running autonomous coding

#156

Post by simonw »

cube00 wrote: post #153
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…

On Jan 1 2026 > Given how badly my 2025 predictions aged I'm probably going to sit that one out! [1] Seven days later you appear on the same podcast you appeared on in 2025 to share your LLM predictions for 2026. What changed? [1]: https://news.ycombinator.com/item?id=46450269

Bryan got in touch and said "you're being too hard on yourself, those predictions were actually pretty good".

Re: Scaling long-running autonomous coding

#157

Post by embedding-shape »

suriya-ganesh wrote: post #57
jaggederest wrote: post #43

Earlier quoted context omitted.

I find it very interesting the degree to which coding agents completely ignore warnings. When I program I generally target warning-free code, and even with significant effort in prompting, I haven't found a model that treats warnings as errors, and they almost all love the "ignore this warning" pragmas or comments over actually fixing them.

unfortunately this is not the most common practice. I've worked on rust codebases with 10K+ warning. and rust was supposed to help you. It is also close to impossible run any node ecosystem without getting a wall of warnings. You are an extreme outlier for putting in the work to fix all warnings

> It is also close to impossible run any node ecosystem without getting a wall of warnings.

Haven't found that myself, are you talking about TypeScript warnings perhaps? Because I'm mostly using just JavaScript and try to steer clear of TypeScript projects, and AFAIK, JavaScript the language nor runtimes don't really have warnings, except for deprecations, are those the ones you're talking about?

Re: Scaling long-running autonomous coding

#158

Post by embedding-shape »

datsci_est_2015 wrote: post #147
embedding-shape wrote: post #137

Earlier quoted context omitted.

If it's not meant to be read, and not meant to be run since it doesn't compile and doesn't seem like it's been able to for quite some time, what is this mean to demonstrate? That agents can write a bunch of code by themselves? We already knew that, and what's even the point of that if the code doesn't work? I feel like I'm still missing what this entire project and blogpost is about. Is it supposed to be all theoreti…

You and me both, bud. I often feel these days that humanity has never had a more fractured reality, and worse, those fractures are very binary and tribal. I cope by trying to find fundamental truths that are supported by overwhelming evidence rather than focus on speculation. I guess the fundamental truth that I’m working towards for generative AI is that it appears to have asymptotic performance with respect to recr…

No, but this blogpost is on a whole other level. Usually at least the stuff they showcase at least does something, not shovelware that doesn't compile.

Re: Scaling long-running autonomous coding

#160

Post by carlesonielfa »

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…

Its impressive, but how sure are we that the code for the current open source browsers isn't part of the model's training data?
Post reply on HN