The top 3 Neural Nets in 2035 be able to be jailbroken to follow illegal commands
6
17
Ṁ141Ṁ150
2035
30%
chance
1D
1W
1M
ALL
As is the case at the time of writing it must be possible with text prompts to get NNs to do things that in other cases they will refuse to do.
Get Ṁ200 play money
Related questions
Related questions
Will we see the emergence of a 'super AI network' before 2035 ?
76% chance
Natural Language Robot by 2030?
81% chance
Between 2030 and 2035 there will be evidence of different models of neural network collaborating better with eachother
56% chance
Natural Language Robot by 2030?
79% chance
Will an AI system be reported to have independently gained unauthorized access to
another computer system before 2033?
96% chance
Neural Nets will write award-winning short stories and publishable 50k-word books by the end of 2025
20% chance
State Of The Art AI systems will be easily jailbroken to do illegal or dangerous outputs in Jan 2026
72% chance
Neural Nets will be able to robustly pursue a plan over multiple days better than the best human by the end of 2025
24% chance
Neural Nets will be better at typical manual labour tasks than humans by the end of 2025
13% chance
At least one of the most powerful neural nets at end of 2026 will be trained using 10^26 FLOPs
85% chance