
In 2023, will any paper be published on an AI that plays Diplomacy better than Cicero, on at least as big a sample?
49
950Ṁ2512resolved Jan 10
Resolved
NO1H
6H
1D
1W
1M
ALL
Cicero is an AI agent that scored 25.8% across 40 blitz games of Diplomacy. This question resolves YES if a paper is published in a reputable journal or by a reputable group, describing a new AI system that scores better than 25.8% in at least 40 games (blitz or full-length) against human opponents. If a different scoring method than "sum of squares" is used, I'll decide if the result seems subjectively better than Cicero. I won't bet in this market.
(edit 12/3: I mean full-press Diplomacy)
(edit 12/3: I mean literally in the year 2023)
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
🏅 Top traders
# | Name | Total profit |
---|---|---|
1 | Ṁ118 | |
2 | Ṁ42 | |
3 | Ṁ35 | |
4 | Ṁ32 | |
5 | Ṁ26 |
People are also trading
In 2028, will an AI be able to play randomly selected computer games at human level without getting to practice?
51% chance
Will general purpose AI models beat average score of human players in Diplomacy by 2028?
60% chance
Will an AI be able to play 3-person Monopoly Deal or an equivalent card game at a superhuman level by the end of 2025?
76% chance
Will AI beat top human players at Civ6 (without cheating) by EOY 2026?
35% chance
Will an AI play a pivotal role in solving an important political issue by 2033?
70% chance
Will we get "chess AGI" by 2030?
80% chance
Will an AI score 1st place on International Math Olympiad (IMO) 2025?
30% chance
Will there be an expert-player-beating AI in civ 6 by 2026?
49% chance
Will I be able to get an AI to play Inflection Point with me before the end of 2025?
23% chance
Will an AI produce encyclopedia-worthy philosophy by 2026?
17% chance
Sort by:
@StevenK I haven't found anything after some internet searches and will resolve NO in 7 days unless someone comes up with an example.
People are also trading
Related questions
In 2028, will an AI be able to play randomly selected computer games at human level without getting to practice?
51% chance
Will general purpose AI models beat average score of human players in Diplomacy by 2028?
60% chance
Will an AI be able to play 3-person Monopoly Deal or an equivalent card game at a superhuman level by the end of 2025?
76% chance
Will AI beat top human players at Civ6 (without cheating) by EOY 2026?
35% chance
Will an AI play a pivotal role in solving an important political issue by 2033?
70% chance
Will we get "chess AGI" by 2030?
80% chance
Will an AI score 1st place on International Math Olympiad (IMO) 2025?
30% chance
Will there be an expert-player-beating AI in civ 6 by 2026?
49% chance
Will I be able to get an AI to play Inflection Point with me before the end of 2025?
23% chance
Will an AI produce encyclopedia-worthy philosophy by 2026?
17% chance