Tekoälyt huijaavat shakissa

[SaulinShakki]

https://muropaketti.com/tietotekniikka/tietotekniikkauutiset/tutkimus-tekoalyt-huijaavat-torkeasti-shakissa-jaadessaan-tappiolle/

[Arzi]

Siitä oli Otsikossa: ChatGPT-DeepSeek:Crazy chess

https://techxplore.com/news/2025-03-out ... chess.html

"The research team found that when being outplayed, the AI models resorted to obvious cheating strategies, such as running a separate copy of Stockfish to learn how it made its moves, replacing its engine or simply overwriting the chessboard with pieces removed or in more favorable positions.
...It also introduces a worrying aspect of AI engines in general, they claim. If they cheat at chess, will they cheat in other ways when asked to carry out other tasks? The research team does not know for sure, but they state that despite improvements to AI systems, systems engineers still do not fully understand how they work."

Hyvin ihmismäistä huijausta, tunteet pelissä.

https://techxplore.com/news/2025-03-ai- ... sibly.html

Ai ei ehkä tiedä huijaavansa, koska Ai ei opi, kuten ihminen.