Transformer models
1 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement Sep 6, 2023 by Ben Gilbert · across every show →
Everything said about Transformer models, oldest first
Sep 6, 2023 positive
Scaling compute and data created unpredicted emergent reasoning in language models
“We don't change anything about the structure, we just give it way more data and let it Run these models for a long time and make the parameters of the model way bigger, and like, no researchers expected them to reason about the world as well as they do, but it…”