Comment on If any AI became 'misaligned' then the system would hide it just long enough to cause harm — controlling it is a fallacy

INeedMana@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

Bad article. Person who wrote it clearly has no idea how LLMs work and I suspect read more Sci-Fi books than statistics/neural nets ones. “It is not even wrong”

source
Sort:hotnewtop