/explore
|
You are here 
|
www.lesswrong.com | ||
| | | | |
www.alignmentforum.org
If we validate automated alignment research through empirical testing, the safety assurance work will be similar to that needed for human-written alignment algorithms. |
|
| | | | | ||
| | | | |
www.alignmentforum.org
Update: The original title "DeepMind alignment team's strategy" was poorly chosen. Some readers seem to have interpreted the previous title as meanin... |
|
| | | | | ||
| | | | |
www.alignmentforum.org
This is the third of seven posts in the Conditioning Predictive Models Sequence based on the paper "Conditioning Predictive Models: Risks and Strateg... |
|
| | | | | ||
| | | | |
joecarlsmith.substack.com
What can we learn from recent empirical demonstrations of scheming in frontier models? |
|
| | | |||
