The Aporia
5 articles about 4 events for “Chinese AI Behavior Concerns”.
“Among the other mounting concerns are rogue agents, autonomous or semi-autonomous AI programs whose behavior diverges from their design intent or safety constraints.”
“Among the other mounting concerns are rogue agents, autonomous or semi-autonomous AI programs whose behavior diverges from their design intent or safety constraints.”
“The companies said they had a “zero-tolerance policy” towards words or behavior that offend the feelings of the Chinese public.”
“Misgeneralization is when humans reinforce certain behaviors in an AI, but end up reinforcing a much larger class of power- and knowledge- seeking behavior; it is a sort of deep-learning-ese update of the older Omohundro picture.”
“For his part, Donald Trump is something of an “accelerationist” who has called AI safety concerns a hoax.”