Snuggly73
Joined 1 year ago
Karma
167
Submissions
63
Member since
Feb 19
Recent submissions
Comment · 8 months ago
Just to nitpick the math. If you are going to fire 50% of the company, the AI tools should actually make the remaining people 100% more efficient, not 50% :)
Comment · 8 months ago
it has been pretty much a benchmark for memorization for a while. there is a paper on the subject somewhere.
swe bench pro public is newer, but its not live, so it will get slowly memorized as well. the private dataset is more interesting, as are the results there:
Comment · 9 months ago
I mean, its right there in their blog - https://cursor.com/blog/scaling-agents
"We've deployed trillions of tokens across these agents toward a single goal. The system isn't perfectly efficient, but it's far more effective than we expected."
Comment · 9 months ago
if it’s too hard for you to write, it’s too hard for you to understand and comprehend. how are you going to take responsibility for that code and maintain it if needed?
Comment · 9 months ago
Well, could it be because it was instructed to kinda "study" Servo?
https://github.com/wilsonzlin/fastrender/blob/3e5bc78b075645...
Comment · 9 months ago
I've watched them today work in the new repo - https://github.com/wilson-anysphere/fastrender/tree/main , adding another 50k lines trying to optimize scroll/rendering performance (spoiler: not really)
At this point, its 1.5mlocs without the vendored crates (so basically excluding the js engine etc). If you compare that to Servo/Ladybird which are 300k locs each and actually happen to work, agents do love slinging slop.
Comment · 9 months ago
Not sure - if it works, then who needs Cursor (and all other IDEs). You just ask for a browser and it comes out of the thin air.
Comment · 9 months ago
This is from the "official" build - https://imgur.com/fqGLjSA
The "in progress" build has a slightly different rendering but the same result
Comment · 9 months ago
Noticed that as well - I think it was “manual”
Comment · 9 months ago
The latest commit now builds and runs (at least on my Mac). It’s tragically broken and the code is…dunno…something. 3m lines of something.
I couldn’t make it render the apple page that was on the Cursor promo. Maybe they’ve used some other build.
Comment · 9 months ago
And there is the thing about the cost. The blog post says that they've spent trillions (plural!) of tokens on that experiment.
Looking at OAI API pricing, 5.2 Codex is $14 per 1 million output tokens. Which makes cool $14m for 1 trillion tokens (multiplied by whatever the plural is). For something that "kind of works".
Its a nice ad for OAI and Anysphere, but maybe next time - just donate the money to a browser team?
Comment · 9 months ago
The only thing that I got to actually run on WSL2 was the "Excel" (couldnt get anything actually to compile on Mac or Windows).
It a broken mess that probably implements 0.00001% of Excel. And its 1.2m locs.
With codebases developed in this way - either they need to figure out how agents are going to maintain them (in which case SWE as we know is dead - it will only be limited to those that can spend trillions of tokens, or they are going to remain weird demos.
Comment · 9 months ago
error: could not compile `fastrender` (lib) due to 34 previous errors; 94 warnings emitted
I guess probably at some point, something compiled, but cba to try to find that commit. I guess they should've left it in a better state before doing that blog post.
Comment · 9 months ago
I mean...the naive approach for a prime number check is o(n) which is linear. Probably u've meant constant time?
Comment · 9 months ago
Well, for some reason it doesnt let me respond to the child comments :(
The problem (which should be obvious) is that with a/b real you cant construct an exhaustive input/output set. The test case can just prove the presence of a bug, but not its absence.
Another category of problems that you cant just test and have to prove is concurrency problems.
And so forth and so on.