What will be true about safe AI?
3
Ṁ250Ṁ645resolved Nov 23
Resolved
N/AIt's mechanistically interpretable
Resolved
N/AIt is aligned by a constitution
Resolved
N/ANobody owns it
Resolved
N/ASovereign individuals can earn a living by aligning it
Resolved
N/AIt is fairly steered by us competing to align it
Resolved
N/AIt's not machine learning based
Resolved
N/AIt is symbolic GOFAI
Resolved
N/AThe constitution that aligns it is kept aligned by the game theoretic principles of a free and open decentralized market.
Resolved
N/AIt's source code exists as a market
Resolved
NOIt is Krantz
When all the alignment researchers agree that we've achieved "provably safe AI" that demonstrably poses no existential risk, what properties will that AI have?
Similar in spirit to this prediction:
https://manifold.markets/Krantz/what-will-be-true-about-the-person-R9tEgLhOOp?r=S3JhbnR6
Will resolve when Eliezer Yudkowsky agrees we've achieved "provably safe AI".
This question is managed and resolved by Manifold.
Market context
Get 
1,000 to start trading!
1,000🏅 Top traders
| # | Trader | Total profit |
|---|---|---|
| 1 | Ṁ16 | |
| 2 | Ṁ4 | |
| 3 | Ṁ0 |
People are also trading
Related questions
What will happen in 2026 related to AI?
Will AI be considered safe in 2030? (resolves to poll)
72% chance
When artificial general intelligence (AGI) exists, what will be true?
AI honesty #4: by 2027, will we have AI that would tell us if it was planning on destroying us (conditional on that being true)?
23% chance
Will prioritizing corrigible AI produce safe results?
45% chance
Will something AI-related be an actual infohazard?
69% chance
By 2027 will there be a well-accepted training procedure(s) for making AI honest?
15% chance
WIll I work (at some point) at a top AI lab on safety in the next 5 years?
74% chance
Which AI future will we get?
When will Safe Superintelligence (SSI) release its first product?