Explore >> Select a destination
|
You are here 
|
joecarlsmith.com | ||
| | | | |
www.lesswrong.com
|
|
| | | | | This is Section 6 of "Scheming AIs." | |
| | | | |
www.alignmentforum.org
|
|
| | | | | Evan et al argue for developing "model organisms of misalignment" - AI systems deliberately designed to exhibit concerning behaviors like deception o... | |
| | | | |
blog.redwoodresearch.org
|
|
| | | | | More thoughts on making deals with schemers | |
| | | | |
scottaaronson.blog
|
|
| | | I have some exciting news (for me, anyway). Starting next week, I'll be going on leave from UT Austin for one year, to work at OpenAI. They're the creators of the astonishing GPT-3 and DALL-E2, which have not only endlessly entertained me and my kids, but recalibrated my understanding of what, for better and worse,... | ||
