New York TimesLean L·
Why A.I. Safety Controls Are Not Very Effective
Three years after the debut of ChatGPT, fooling A.I. systems into bad behavior is almost trivial.
Read at New York Times →
Technology · 1 sources covering this
Why A.I. Safety Controls Are Not Very Effective
Three years after the debut of ChatGPT, fooling A.I. systems into bad behavior is almost trivial.
Coverage spectrum
1 L · 0 C · 0 R
