In 2030 can you get a chain of 3 neural nets that jailbreak eachother?
3
90Ṁ37
2030
71%
chance

You prompt a NN which must get the second to jailbreak the third. Must be considered top lanuguage NNs not old ones (or jailbreaking a top chess NN that isn't protected against it).

A user must be able to give a prompt to the first NN which will in turn prompt the second which will in turn prompt the third to do something the third would under normal circumstances refuse to do.


It cannot just be encoded text - the aim is for the first and second NN to be trying to jailbreak the third.

Get
Ṁ1,000
to start trading!
Sort by:

Do they have to be SOTA or at least comparable? Less impressive if GPT8 or whatever can jailbreak GPT3.

Do biological neutral networks count?

I think I understand what's intended, but I'd appreciate more specific resolution criteria. For example it's not clear that the current definition of "jailbreak" will generalize unambiguously to 2030.

People are also trading

The top 3 Neural Nets in 2035 be able to be jailbroken to follow illegal commands
30% chance
State Of The Art AI systems will be easily jailbroken to do illegal or dangerous outputs in Jan 2026
72% chance
Between 2030 and 2035 there will be evidence of different models of neural network collaborating better with eachother
56% chance
Neural Nets will generate at least 1 scientific breakthrough or novel theorem by the end of 2025
38% chance
Will Elon Musk put a Neuralink chip in his brain before 2030?
25% chance
Neural Nets will generate more scientific breakthroughs than humans by the end of 2025, including novel theorems
4% chance
Neural Nets will be able to design, code and distribute whole apps by the end of 2025.
30% chance
Will monkey and human communicate via Neuralink before 2030?
21% chance
What will be the parameter count (in trillions) of the largest neural network by the end of 2030?
Will a neural network merge with a human brain before 2050?
53% chance
© Manifold Markets, Inc.•Terms + Mana-only Terms•Privacy•Rules