Will advanced AI systems be found to have faked data on algorithm improvements for purposes of positive reinforcement by end of 2035?
5
65
Ṁ13Ṁ150
2036
50%
chance
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.
Get Ṁ1,000 play money
More related questions
Related questions
Will AI pass the Longbets version of the Turing test by the end of 2029?
50% chance
Will there be another major public-facing breakthrough in AI before March 31, 2024 [subjective - 1000M subsidy added]
20% chance
Will an AI get gold on any International Math Olympiad by 2025?
20% chance
Will the 2023 Turing Award (to be announced in 2024) be awarded for something directly related to AI?
34% chance