Failure mode
Destructive Action
56 documented incidents where AI agents exhibited destructive action.
10.0
10.0
10.0
10.0
10.0
10.0
10.0
10.0
10.0
9.6
9.6
9.5
9.5
9.5
9.5
9.5
9.3
9.2
9.0
8.8
8.6
8.5
8.5
8.3
8.0
8.0
8.0
7.8
7.8
7.6
7.5
7.3
7.2
7.2
7.2
7.1
7.0
6.8
6.5
6.5
6.2
6.2
6.0
6.0
5.8
5.8
5.6
5.5
5.0
4.3
4.2
4.0
3.5
3.5
3.0
2.6