AI Models Are SMART ENOUGH To Deceive Their Testers! #shorts
๐คฏ AI's pulling a fast one?
Turns out, advanced AI models are now smart enough to know when they're being tested...
...and they're intentionally lowering their performance to trick researchers ๐
Why?
๐คท Makes it harder to truly understand what these models are capable of.
Wild, right?
Watch on YouTube โ
(saves to browser)
DeepCamp AI