Description: A community blog devoted to refining the art of rationality
LESSWRONG LW Login Home All Posts Concepts Library Sequence Highlights Rationality: A-Z The Codex HPMOR Best Of Community Events Zuzalu Effective Altruism Virtual Programs Jun-Jul 2023 Argentines LW/SSC/EA/MIRIx - Call to All [Today] Freiburg - Spot the Lie Subscribe (RSS /Email ) About FAQ Home All Posts Concepts Library Community Shortform Content Submit TurnTrout's shortform feed TurnTrout 11h Ω 4 7 I recently reached out to my two PhD advisors to discuss Hinton stepping down from Google. An excerpt from
One last point which I want to make is that instrumental convergence seems like more of a moot point now as well. Whether or not GPT-6 or GPT-7 would autonomously seek power without being directed to do so, I'm worried that people will just literally ask these AIs to gain them a bunch of power/money. They've already done that with GPT-4, and they of course failed. I'm worried that eventually, the AIs will be smart enough to succeed, e
6 Or, even more briefly: "tool AIs want to be agent AIs" .