News for hackers. Stuff that matters.
Re:When AI Benchmarks Plateau: A Systematic Study of Benchma... by 827a on Wednesday August 05, 2026 @09:49AM (#49182884)
Coding is an extremely verifiable and loopable task, like math (in fact, all of the math that these models has done has been through the lens of Lean, which is itself just coding). I am talking about their capabilities in tasks that are more general, the execution of which represent the vast majority of economic value generation in the world.

There are no comments on this comment yet.