Source: “Evan Hubinger said that while current risks are low, there’s a 10% chance AI could “kill all humans” in the future without proper safeguards.”
Source: “Evan Hubinger said that while current risks are low, there’s a 10% chance AI could “kill all humans” in the future without proper safeguards.”
I love how these scenarios never explain the hardware side. How can a software become infinitely smart without infinite hardware?