/explore
|
You are here 
|
www.alignmentforum.org | ||
| | | | |
www.lesswrong.com
Evan et al argue for developing "model organisms of misalignment" - AI systems deliberately designed to exhibit concerning behaviors like deception o... |
|
| | | | | ||
| | | | |
www.lesswrong.com
This post heavily overlaps with "how might we safely pass the buck to AI?" but is written to address a central counter argument raised in the comment... |
|
| | | | | ||
| | | | |
www.lesswrong.com
This is Section 6 of "Scheming AIs." |
|
| | | | | ||
| | | | |
deepmind.google
We ask the question: "What is the optimal model size and number of training tokens for a given compute budget?" To answer this question, we train models of various sizes and with various numbers... |
|
| | | |||
