Transformers are not suitable architectures for predicting the physical world because they are fundamentally designed for token prediction rather than abstract representation learning.

causalpending

Speaker

Unknown Speaker (video narrator/analyst)

Evidence Quote

“using a transformer to basically predict the physical world just doesn't work because of the architecture”

Source

Metas AI Boss Says He DONE With LLMS...— TheAIGRID
Created: 8/11/2026, 5:05:19 AM

Your notes

Loading notes...