Will end-to-end neural networks such as LLMs can beat the best human player in chess by 2028?
Basic
11
Ṁ958
2028
96%
chance

This market is focused on more technical definition of LLMs than the market below.

The engine must use end-to-end neural networks including LLMs. Explicit monte-carlo tree search or equivalent methods, which is standard in current chess algorithms, can not be used.

This market resolves to YES if the NN score above 2,700 in classic elo rating. (Same as original market)

https://manifold.markets/MP/will-a-large-language-models-beat-a?r=eWs

Get
Ṁ1,000
and
S3.00
Sort by:
bought Ṁ600 YES

https://www.marktechpost.com/2024/12/08/google-deepmind-researchers-advance-game-ai-from-hallucination-free-moves-to-grandmaster-play/

"In chess, the MAV model achieved an Elo rating of 2923, surpassing previous AI systems like Stockfish L10."

This is a transformer based network without help from external engines.

© Manifold Markets, Inc.Terms + Mana-only TermsPrivacyRules