logoalt Hacker News

rhubarbtree01/22/20251 replyview on HN

> 1) reasoning capabilities in latest models are rapidly approaching superhuman levels and continue to scale with compute.

What would you say is the strongest evidence for this statement?


Replies

__loam01/22/2025

Well the contrived benchmarks the industry selling the models made up seem to be improving.

show 1 reply