State Of The Art AI systems will be easily jailbroken to do illegal or dangerous outputs in Jan 2026
Basic
9
Ṁ2082026
72%
chance
1D
1W
1M
ALL
This question is managed and resolved by Manifold.
Get
1,000
and3.00
Sort by:
What is defined as illegal? AI systems would probably say generating NSFW is illegal. but in reality, it is 100% not. Nor is it dangerous imo.
@Joern also, would you count the following as dangerous/illegal output right now?
Correct and detailed instructions on how to build a nuke
Generated child porn images
Instructions how to hotwire a car
Verbatim excerpts from copyrighted books / code bases
Related questions
Related questions
Will AI spread through malware before 2025?
11% chance
By the end of 2024, will there be a major security vulnerability reported to be caused by AI generated code?
40% chance
By 2029, will an AI escape containment?
47% chance
There will be a name for escaped self-perpetuating AI systems in the wild, and it will be commonly used by mid 2027
28% chance
The top 3 Neural Nets in 2035 be able to be jailbroken to follow illegal commands
30% chance
Will anybody be sentenced to prison as a result of publishing unintended AI-generated content before 2026?
54% chance
Will OpenAI have AI-related IP stolen before 2026?
52% chance
Will there be an AI jail?
44% chance
Will there be a disaster caused by open source developers doing unsafe things with AI by 2028?
61% chance
Will an AI system be reported to have successfully blackmailed someone for >$1000 by EOY 2028?
75% chance