@benediktpeterseim@mathstodon.xyz
Post #2995270
2026-04-21 13:52 UTC
@bgavran@mathstodon.xyz “The system AlphaZero utilises the game structure during training and reaches superhuman ELO (>3400) with ~30x fewer parameters than GPT-4 (<60 million vs 1.8 trillion).” — I guess that’s supposed to be a “30.000x fewer”? (Which is quite immense.)
Replies (1)
-
@bgavran@mathstodon.xyz 2026-04-21 15:05
@benediktpeterseim@mathstodon.xyz Oh gosh, yes! That's an even starker difference.