Forget fancy benchmarks, this is the real eval!

GPT-4.5 just nailed the “ball bouncing in a spinning hexagon” challenge in one shot—@edwinarbus simply asked it to be more creative! ⬡✨ https://t.co/I8tF6m2X14

— Romain Huet (@romainhuet) 27 février 2025

Forget fancy benchmarks, this is the real eval! GPT-4.5 just nailed the “ball bouncing in a spinning hexagon” challenge in one shot—
@edwinarbus simply asked it to be more creative! ⬡

→ View original post on X — @romainhuet,