Re:LaMDA is not sentient
by amai on Monday June 13, 2022 @02:57PM
(#31729996)
Would LaMDA be able to understand, when it is talking to itself? That would mean self-awareness to me. So what would happen if one would just repeat the answers of LaMDA and presented them as input prompts like an echo. Would it recognize itself and stop talking? Would it start talking to itself? I think that would be an intriguing experiment.
[ Parent
| on HN ]
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.