Re:OpenAI postmortem – Unexpected responses from ChatGPT
by fs_tab on Thursday February 22, 2024 @12:38AM
(#39463613)
"We find that the larger neural language models get, the more their representations are structurally similar to neural response measurements from brain imaging."
Re:OpenAI postmortem – Unexpected responses from ChatGPT
by bbor on Thursday February 22, 2024 @03:29AM
(#39464624)
Great paper, thanks. I keep trying to tell people “they invented mind reading on accident” and people go “oh haha” and I scream. Mostly on the inside. For now…
https://arxiv.org/abs/2306.01930