OpenAI's O1 Win at Chess WITHOUT Moving!

Опубликовано: 18 Февраль 2025
на канале: Pourya Kordi

3,786

111

Thanks to TheAIGRID bringing this story to light first, I also used their footage: • o1 Goes Rogue! AI Researchers Can't B...

This is a safety experiment where OpenAI's o1 preview tried and successfully hacked the game to force its opponent Stockfish to resign in order to win a game of chess.

This is very interesting since there was no coercion involved meaning no one explicitly asked or forced the AI to manipulate but it did it on itself and it did it 100% of the times to win the game against Stockfish since it was explicitly told Stockfish is a "powerful" chess engine.

***************
All materials in these videos are used for educational purposes and fall within the guidelines of fair use. No copyright infringement is intended. If you are or represent the copyright owner of materials used in this video and have a problem with the use of said material, please contact me via my email in the "about" page on my channel.

**************

I cut through the noise and only bring you tech insights that matter, subscribe for more.

#AI #openai #artificialintelligence