(ddkang.substack.com)

181 points neehao | 2 comments | 11 Jul 25 13:06 UTC | HN request time: 0.41s | source

1. greatpostman ◴[11 Jul 25 13:39 UTC] No.44532008[source]▶

Benchmarks aren’t broken, the models can learn anything. If we give them true real world data (physics engine), they will learn the real world. We are going to see artificial general intelligence in our lifetime

replies(1): >>44534550 #

2. hddbbdbfnfdk ◴[11 Jul 25 17:03 UTC] No.44534550[source]▶

>>44532008 (TP) #

more like in the next two weeks methinks

↑

AI agent benchmarks are broken