Will there be a well accepted formal definition for honesty in AI by 2027?
Mini
9
Ṁ2062027
21%
chance
1D
1W
1M
ALL
Doesn't need total acceptance
If there are multiple similar competing definitions (e.g. similar to the current situation with differential privacy) I'll resolve yes
Get Ṁ600 play money
Related questions
Related questions
Will an AI be able to convert recent mathematical results into a fully formal proofs that can be verified by a mainstream proof assistant by 2025?
24% chance
AI honesty #3: by 2027 will we have interpretability tools for detecting when an AI is being deceptive?
62% chance
AI honesty #2: by 2027 will we have a reasonable outer alignment procedure for training honest AI?
25% chance
By 2027 will there be a well-accepted training procedure(s) for making AI honest?
16% chance
Will there be a well accepted formal definition of value alignment for AI by 2030?
25% chance
AI honesty #1: by 2027 will we have AI that doesn't hallucinate random nonsense?
73% chance
Will a major AI company acknowledge the possibility of conscious AIs by 2026?
62% chance
In which year will a majority of AI researchers concur that a superintelligent, fairly general AI has been realized?
Will any AI be legally recognized by any country's government as being a "person" deserving of some rights before 2029?
34% chance
An AI is trustworthy-ish on Manifold by 2030?
46% chance