Exploiting the most prominent AI agent benchmarks
(news.ycombinator.com)
1.
2.
How We Broke Top AI Agent Benchmarks: And What Comes Next
(news.ycombinator.com)
3.
In Memoriam: John W. Addison, my PhD advisor
(news.ycombinator.com)
4.
5.
LoGeR – 3D reconstruction from extremely long videos (DeepMind, UC Berkeley)
(news.ycombinator.com)