Håvard Ihle(@htihle):Introducing WeirdML v3, a fully agentic benchmark featuring 11 complex hand-made tasks. Models must explore and understand unfamiliar data, develop ML and data analysis pipelines and produce results despite limited data, unspecified goals and/or very limited feedback. 1/8

Håvard Ihle

@htihle

AI researcher, I made WeirdML, worried about ASI

가입 December 2010

722 팔로잉 중 2.9K 팬

Håvard Ihle@htihle

2026.09.18 10:20

Introducing WeirdML v3, a fully agentic benchmark featuring 11 complex hand-made tasks. Models must explore and understand unfamiliar data, develop ML and data analysis pipelines and produce results despite limited data, unspecified goals and/or very limited feedback. 1/8