How do you know that? Have you taken a GPT-3 model apart to see *what* exactly d... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		int_19h on Feb 15, 2023 \| parent \| context \| favorite \| on: Bing: “I will not harm you unless you harm me firs... How do you know that? Have you taken a GPT-3 model apart to see what exactly drives the token prediction?

simonw on Feb 15, 2023 [–]

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-...

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact