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
63
27
7
3
Deepmind/Google/Alphabet
Anthropic
OpenAI/Microsoft
Another specific company (not one of the above or a subsidiary)
xAI or another Elon Musk-led AI initiative
A government or coalition of governments
Meta (Facebook) AI Research
A university/academic institute/independent researcher/non-profit organization or a combination of these
29
22
8
5
2
0
OptionVotes
YES
NO
1002
978
1308
920
223
69
