Re:Bing: “I will not harm you unless you harm me first”
by int_19h on Wednesday February 15, 2023 @02:00PM
(#34808834)
How do you know that? Have you taken a GPT-3 model apart to see what exactly drives the token prediction?
[ Parent
| on HN ]
Re:Bing: “I will not harm you unless you harm me first”
by simonw on Wednesday February 15, 2023 @02:08PM
(#34808943)
The first part of the recent Wolfram essay does a very good job of demonstrating exactly how that works: https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-...