Will there be a program achieving at least 50% accuracy on the Abstraction and Reasoning Corpus by the end of 2023?
6
150Ṁ230
resolved Jan 15
Resolved
NO

https://github.com/fchollet/ARC

Ancient Markets
New Year's Resolutions 2024
Get
Ṁ1,000
to start trading!

🏅 Top traders

#NameTotal profit
1Ṁ25
2Ṁ11
3Ṁ9
4Ṁ8
5Ṁ8

People are also trading

ARC-AGI-2 Top Score >=50% in 2025?
19% chance
AI solves the Abstraction and Reasoning Corpus (ARC) by 2028
54% chance
Will the Center for AI Policy reach their minimum funding goal by 6/16/2025?
59% chance
Will any AI model score above 95% on GRAB by the end of 2025?
41% chance
Will an AI system capable of doing 50% of knowledge job arrive by 2027?
41% chance
Will AI pass the Winograd schema challenge by the end of 2025?
86% chance
Will over 20% of Program on AI and Reasoning (PAIR) students ACROSS ALL YEARS be active manifold users by EOY 2024?
41% chance
In 2029, will any AI be able to construct "reasonably" bug-free code of >= 10k LOC from a natural language specification? (Gary Marcus benchmark #4)
80% chance
Will openAI have the most accurate LLM across most benchmarks by EOY 2024?
37% chance
Will AI pass the Winograd schema challenge by the end of 2024?
64% chance
Sort by:

⚠Unreceptive to ping ; AFK Creator

📢Resolved to NO

@MichaelHodel Can you please resolve this question? I appreciate it.

50% of what? There are 800 questions available in the repository (400 training; 400 evaluation), and you could trivially write a program that is >50% accurate just by hardcoding the solutions to those. (Probably contrary to the spirit of this market, but technically valid.) The ARCathon competition tests entrants on an additional 100 unpublished problems.

Linking in some related markets:

I wonder whether GPT-4 has been tested on this, does anyone know?

People are also trading

ARC-AGI-2 Top Score >=50% in 2025?
19% chance
AI solves the Abstraction and Reasoning Corpus (ARC) by 2028
54% chance
Will the Center for AI Policy reach their minimum funding goal by 6/16/2025?
59% chance
Will any AI model score above 95% on GRAB by the end of 2025?
41% chance
Will an AI system capable of doing 50% of knowledge job arrive by 2027?
41% chance
Will AI pass the Winograd schema challenge by the end of 2025?
86% chance
Will over 20% of Program on AI and Reasoning (PAIR) students ACROSS ALL YEARS be active manifold users by EOY 2024?
41% chance
In 2029, will any AI be able to construct "reasonably" bug-free code of >= 10k LOC from a natural language specification? (Gary Marcus benchmark #4)
80% chance
Will openAI have the most accurate LLM across most benchmarks by EOY 2024?
37% chance
Will AI pass the Winograd schema challenge by the end of 2024?
64% chance
© Manifold Markets, Inc.•Terms + Mana-only Terms•Privacy•Rules