Elon Musk Archive
Yann LeCun
Yann LeCun
@ylecun · 9. März 2024
* Language is low bandwidth: less than 12 bytes/second. A person can read 270 words/minutes, or 4.5 words/second, which is 12 bytes/s (assuming 2 bytes per token and 0.75 words per token). A modern LLM is typically trained with 1x10^13 two-byte tokens, which is 2x10^13 bytes.
Parmita MishraParmita Mishra@parmita· 8. März 2024
This is an essential point people seem to misrepresent.
Parmita Mishra
Elon Musk
Elon Musk
@elonmusk
Yes
20:28 · 9. März 2024 · 44.842 Aufrufe
165
22
620