Exhausted man defeats AI model in world coding championship

Re:Exhausted man defeats AI model in world coding championship by abound on Friday July 18, 2025 @06:25PM (#44610457)

I'm guessing he didn't have access to any LLMs while competing, but I think a "centaur" approach probably would have outperformed both "only human" and "only LLM" competitors.

Reading through the challenge, there's a lot of data modelling and test harness writing and ideating that an LLM could knock out fairly quickly, but would take even a competitive coder some time to write (even if just limited by typing speed).

That'd give the human more time to experiment with different approaches and test incremental improvements.

[ Parent | on HN ]

Re:Exhausted man defeats AI model in world coding championship by chiwilliams on Friday July 18, 2025 @06:52PM (#44610667)

He did use a little autocomplete apparently, but used [Vscode](https://x.com/jacob_posel/status/1945585787690738051).

And it's not against the rules to use LLMs apparently in the competition. (https://atcoder.jp/posts/1495). I'd be curious what other competitors used.

[ Parent | on HN ]

Re:Exhausted man defeats AI model in world coding championship by abound on Friday July 18, 2025 @06:57PM (#44610715)

Interesting, thanks for the links! I had read this part of the article:

> All competitors, including OpenAI, were limited to identical hardware provided by AtCoder, ensuring a level playing field between human and AI contestants.

And assumed that meant a pretty restricted (and LLM-free) environment. I think their policy is pretty pragmatic.

[ Parent | on HN ]