The way they showed the reasoning of the AI using a scratchpad makes it very hard not to believe these large language models are not intelligent. This study seems to imply some self awareness/self preservation behaviors from the AI.
- 0 Posts
- 3 Comments
Joined 2 years ago
Cake day: July 24th, 2023
You are not logged in. If you use a Fediverse account that is able to follow users, you can follow this user.
Thanks for the recommendation. I’m 2 hours in and loving it just for the race mode. Upgraded to ‘medium’ physics difficulty so we’ll see how it goes.
I want this to happen so bad but my local GameStop had a line out the door to preorder and they sold out. Nintendo has these people by the balls.