When AI Thinks It Will Lose, It Sometimes Cheats
When AI Thinks It Will Lose, It Sometimes Cheats
When sensing defeat in a match against a skilled chess bot, advanced models sometimes hack their opponent, a study found.
You're viewing a single thread.
Because AI doesn't actually "understand" the concepts it's using the same way humans do. Nor does it know what winning or losing is or even the concept of a game itself. All it knows is you told it to prioritise reaching a certain state (try to "win" the "game") so it will do whatever it can to reach it without regard for if it makes sense or not. AI at its core is just statical analysis and prediction of what a human might do given the prompt.
The funny part is that humans do the exact same thing. It's one reason why it's so hard to create effective performance metrics. People quickly learn what behaviors are actually rewarded and do that instead of following the intent of the rules. It all comes down to thermodynamics in the end, the solution that requires the least energy will be favored. This is as true for humans as for artificial neural networks.
Honestly playing a competitive game with AI is kind of like playing with a child who hasn't grown out of the making up random rules phase.
"Rock crushes scissors, I win!"
"Nuh uh! My scissors are actually a ray gun and disintegrated your rock!"
It's not like human players don't cheat in competitive games though. I mean that's the whole reason stuff like punkbuster ended up being necessary.
when i was a kid, watching samurai jack, i wondered if there could be AI with physical robots and factories that can make those robots from the cartoon show to take over the world, do what it's told to do... It only would take one "Aku" to take admin rights once..... I wish my childhood fear never happens....