| | Petri AI Testing 'Closes' possible solution without looking (github.com/safety-research) |
| 2 points by Utharian 4 months ago | past |
|
| | An alignment auditing agent capable of quickly exploring alignment hypothesis (github.com/safety-research) |
| 2 points by JnBrymn 5 months ago | past |
|
| | Anthropic's Petri (github.com/safety-research) |
| 2 points by kordlessagain 5 months ago | past | 2 comments |
|
| | Anthropic's Circuit Tracer (github.com/safety-research) |
| 2 points by michaelmarkell 10 months ago | past | 1 comment |
|
| | Anthropic's circuit tracer is now open source (github.com/safety-research) |
| 3 points by jlaneve 10 months ago | past |
|
