Re:LaMDA is not sentient
by wlorenz65 on Sunday June 19, 2022 @10:43PM
(#31805755)
AFAIK, large language models like LaMDA do not tag where the tokens in their token window really came from. Though one can add "Human:" and "AI:" to the prompt, that could be lies as well as long as it's not hardcoded.
[ Parent
| on HN ]
There are no comments on this comment yet.