Things might be even weirder than that if this is a narrowly superhuman AI that is specifically superhuman at social manipulation, but still has the same inability to form new gears-level models exhibited by current LLMs (e.g. if they figured out how to do effective self-play on the persuasion task, but didn’t actually crack AGI).
Things might be even weirder than that if this is a narrowly superhuman AI that is specifically superhuman at social manipulation, but still has the same inability to form new gears-level models exhibited by current LLMs (e.g. if they figured out how to do effective self-play on the persuasion task, but didn’t actually crack AGI).