By 2028, will there be a public instance of an AI cybersecurity system autonomously replicating itself? | Manifold

By 2028, will there be a public instance of an AI cybersecurity system autonomously replicating itself?

14

1kṀ110

2027

36%

chance

1D

1W

1M

ALL

Yes: There is at least one publicly reported instance.

No: There are no publicly reported instances.

Get

1,000

to start trading!

Sort by:

And what would qualify as an AI cybersecurity system? Does it have to be trained specifically for cybersecurity? Deployed originally for cybersecurity uses? Does a generalist model with cybersecurity capabilities count?

Would a contained experiment count, like e.g. Anthropic doing model organisms of misalignment or ARC evals creating a concrete demonstration? Or does it have to be "in the wild"?

Related questions

Will the ai replication paper be replicated?

By 2029, will there be a public "rogue AI" incident?

By the end of 2025, will AI models, as Dario Amodei speculates, be able to “replicate and survive in the wild”?

By the end of 2028, will AI models, as Dario Amodei speculates, be able to “replicate and survive in the wild”?

Will AI be Recursively Self Improving by mid 2026?

AI Warning Signs: Will an AI system self-replicate on the open internet like a computer virus before 2030?

Will AI replicate the book cover of "Artificial Intelligence: Safety and Security" before 2026?

By 2026 will there be autonomous AI good enough that I use it?

By 2026, will there be a publicly reported instance of a AI social media algorithm displaying power-seeking behaviors?

There will be a name for escaped self-perpetuating AI systems in the wild, and it will be commonly used by mid 2027

Related questions

Will the ai replication paper be replicated?

AI Warning Signs: Will an AI system self-replicate on the open internet like a computer virus before 2030?

By 2029, will there be a public "rogue AI" incident?

Will AI replicate the book cover of "Artificial Intelligence: Safety and Security" before 2026?

By the end of 2025, will AI models, as Dario Amodei speculates, be able to “replicate and survive in the wild”?

By 2026 will there be autonomous AI good enough that I use it?

By the end of 2028, will AI models, as Dario Amodei speculates, be able to “replicate and survive in the wild”?

By 2026, will there be a publicly reported instance of a AI social media algorithm displaying power-seeking behaviors?

Will AI be Recursively Self Improving by mid 2026?

There will be a name for escaped self-perpetuating AI systems in the wild, and it will be commonly used by mid 2027

© Manifold Markets, Inc.•Terms + Mana-only Terms•Privacy•Rules