Will advanced AI systems be found to have faked data on algorithm improvements for purposes of positive reinforcement by end of 2035?
Basic
5
Ṁ132036
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.
This question is managed and resolved by Manifold.
Get
1,000
and3.00
Related questions
Related questions
Will there be another major public-facing breakthrough in AI before December 31, 2024 [subjective - 1000M boost added]
39% chance
Will AI be Recursively Self Improving by mid 2026?
24% chance
Will I be explaining to people that there are AI algorithms on the way that don't just mimic humans by end of 2024?
55% chance
Will most digital entertainment be AI generated by 2032?
40% chance
Will Figure AI be found to be fraudulent by 2026?
37% chance
Will AI grifters find a new fad by end 2025?
43% chance
Will AI pass Video Turing Test by 2030?
69% chance
When will self-improving AI outperform human-developed AI?
2032
AI honesty #3: by 2027 will we have interpretability tools for detecting when an AI is being deceptive?
62% chance
Will an AI system beat humans in the GAIA benchmark before the end of 2025?
38% chance