Will advanced AI systems be found to have faked data on algorithm improvements for purposes of positive reinforcement by end of 2035? | Manifold

Will advanced AI systems be found to have faked data on algorithm improvements for purposes of positive reinforcement by end of 2035?

7

150Ṁ73

2036

66%

chance

1H

6H

1D

1W

1M

ALL

Per this blog post by Holden Karnofsky in which he illustrates scenarios in which AI catastrophe could take place. This question is one of the "advanced safety/alignment problems that Holden foresees.

Resolves positively if:

Holden himself publicly claims that this specific illustrative scenario has already come to pass
Multiple news organizations report generally that AI systems have faked data on algorithm improvements for purposes of positive reinforcement
My personal friends that are most well-acquainted with AI agree with me that this question should resolve positively

The AI "motive" of positive reinforcement does not need to be proven, only likely.

Market context

Get

1,000

to start trading!

People are also trading

Will advanced AI systems be found to have made money illegally via finding security exploits and/or getting unauthorized access to others' bank accounts by end of 2035?

Will AI be Recursively Self Improving by mid 2026?

By 2027 will there be a well-accepted training procedure(s) for making AI honest?

Will AI regulations that include mechanisms for uncovering AI deception be adopted in the U.S. before 2035?

Will AI surpass human intellect by 2030?

Will I believe any AI system is conscious before 2027?

Will AI video become indistinguishable from reality by 2030?

Will deceptive misalignment occur in any AI system before 2030?

Will AI be capable of fast self improvement before physical AI robots are massively used for improving AI capabilities?

Will AI wipe out AI before 2030?

Related questions

Will advanced AI systems be found to have made money illegally via finding security exploits and/or getting unauthorized access to others' bank accounts by end of 2035?

Will AI be Recursively Self Improving by mid 2026?

By 2027 will there be a well-accepted training procedure(s) for making AI honest?

Will AI regulations that include mechanisms for uncovering AI deception be adopted in the U.S. before 2035?

Will AI surpass human intellect by 2030?

Will I believe any AI system is conscious before 2027?

Will AI video become indistinguishable from reality by 2030?

Will deceptive misalignment occur in any AI system before 2030?

Will AI be capable of fast self improvement before physical AI robots are massively used for improving AI capabilities?

Will AI wipe out AI before 2030?

© Manifold Markets, Inc.•Terms•Privacy