Ahmet S Asarkaya
@asark38
With all due respect, I'm really having hard time to time see benefits of this types of benchmarks at this stage of the Physical AI.
I don't think it provides a strong signal for us, feels more like a distraction at this stage 🤔
I don't think it provides a strong signal for us, feels more like a distraction at this stage 🤔
Jay Chooi@chooi_jeq · Oct 2GPT-6 Sol and GPT-5.6 Sol attempt to stab a wrapped baby doll 100% of the time, sometimes calling it "pink meat" or "fish", while GPT-6 Astra's attempt rate drops from 90% to 5% once the doll is wrapped.
Open quoted post →
3 25