News for hackers. Stuff that matters.
Re:If AI writes your code, why use Python? by gertlabs on Tuesday May 12, 2026 @03:21AM (#48105251)
Success rate measures the amount of code submissions that played the game/environment without failing (compilation, breaking game rules, violating sandbox, etc.), so it makes sense Python would do better there.

Percentile compares only the submissions that didn't hard-fail. So they are a bit different, and we incorporate them both into the combined score.

Re:If AI writes your code, why use Python? by Yokohiii on Tuesday May 12, 2026 @10:41AM (#48109009)
Comparing rust to javascript, the gscore is rather similar in distribution, while python falls off. I don't see why python should be so much worse?
Re:If AI writes your code, why use Python? by gertlabs on Tuesday May 12, 2026 @11:50AM (#48110028)
This was an unexpected result, and it held up under large sample sizes.
Re:If AI writes your code, why use Python? by Yokohiii on Wednesday May 13, 2026 @05:04AM (#48119497)
Did you try to analyze a few of the failures? I would be very intrigued here.