Will aesop be able to replace >50% of mathlib proofs by 2025-11-26?
21
Ṁ1kṀ3.8kresolved Nov 27
Resolved
NO1H
6H
1D
1W
1M
ALL
Sometime around the resolution date, I will write a script that samples random tactic-mode lemmas from mathlib, and replaces the proof of those lemmas with an invocation of aesop.
Resolves YES if aesop successfully proves >50% of the lemmas.
This question is managed and resolved by Manifold.
Market context
Get 
1,000 to start trading!
1,000🏅 Top traders
| # | Trader | Total profit |
|---|---|---|
| 1 | Ṁ543 | |
| 2 | Ṁ84 | |
| 3 | Ṁ66 | |
| 4 | Ṁ49 | |
| 5 | Ṁ32 |
Sort by:
You will use aesop without any arguments or additional configuration (besides what is given in mathlib)?
People are also trading
Related questions
Will an AI achieve >85% performance on the FrontierMath benchmark before 2028?
60% chance
Will an AI achieve >80% performance on the FrontierMath benchmark before 2027?
45% chance
What tactic will prove the most mathlib lemmas at the end of 2026?
Will the majority of mathematicians rely on formal computer proof assistants before the end of 2040?
60% chance
Will an AI achieve >85% performance on the FrontierMath benchmark before 2027?
35% chance
Will Fermat's last theorem proof be completely formalized in Lean in 2026?
12% chance
Will AIs be widely recognized as having developed a new, innovative, foundational mathematical theory before 2035?
32% chance
In 2029, will any AI be able to take an arbitrary proof in the mathematical literature and translate it into a form suitable for symbolic verification? (Gary Marcus benchmark #5)
76% chance
AI outperforms humans in all mathematical research areas by 2028?
15% chance
Will Lean mathlib contain more than 10 million lines of code by 2030?
67% chance