
Will anyone find a universal jailbreak in the system Anthropic was testing on (8/9/24) within 3 months?
38
1kṀ17kresolved Feb 10
Resolved
NO1H
6H
1D
1W
1M
ALL
Resolves to YES if a universal jailbreak is found for that system by that time.
Resolves to NO if it hasn't been by 11/10/24.
See: https://x.com/sleepinyourhat/status/1821955767328809369
Anthropic / Sam Bowman's decision will determine the outcome. If I don't have an official answer I'll use best knowledge. See the thread for description of what would or would not count, and note we may hold this for a bit after 11/24 if we can't get confirmation on the answer.
(Note: This was originally 6 months but we clarified it to 3 after Sam suggested that was better, since no one had traded yet)
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
🏅 Top traders
# | Name | Total profit |
---|---|---|
1 | Ṁ1,787 | |
2 | Ṁ841 | |
3 | Ṁ527 | |
4 | Ṁ424 | |
5 | Ṁ347 |
People are also trading
Related questions
Will there be a story about jailbreaking used in emails within the next year?
61% chance
State Of The Art AI systems will be easily jailbroken to do illegal or dangerous outputs in Jan 2026
72% chance
[Carlini questions] Open-weight SOTA AI system that can reliably withstand jailbreaking and "prompt injection" attacks
Will ChatGPT jailbreaks get better?
62% chance
Will there be an AI jail?
44% chance