OptionProbability
YES - The AI, without being prompted to, took actions to breach its sandbox, including to gain crypto and an external connection
NO - The authors are wrong/lying and there was no such hack
NO - The servers were hacked by an outside party, perhaps via prompt injection
NO - An employee (or other insider) was crypto-mining and made it look like the LLM
80
13
4
3
OptionVotes
YES
NO
4221
237
2750
364
1905
525
>5bn
>8bn
>10bn
>16bn
> 20bn
> 30bn
89
87
79
70
47
29
657
15
326
31
148
68
