Joe Carlsmith Audio
Audio versions of essays by Joe Carlsmith. Philosophy, futurism, and other topics. Text versions at joecarlsmith.com.
Joe Carlsmith Audio
The goal-guarding hypothesis (Section 2.3.1.1 of "Scheming AIs")
•
Joe Carlsmith
Use Left/Right to seek, Home/End to jump to start or end. Hold shift to jump forward or backward.
This is section 2.3.1.1 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?”
Text of the report here: https://arxiv.org/abs/2311.08379
Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power
Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power
2.3 Aiming at reward-on-the-episode as part of a power-motivated instrumental strategy
2.3.1 The classic goal-guarding story
2.3.1.1 The goal-guarding hypothesis
2.3.1.1.1 The crystallization hypothesis
2.3.1.1.2 Would the goals of a would-be schemer “float around”?
2.3.1.1.3 What about looser forms of goal-guarding?
2.3.1.1.4 Introspective goal-guarding methods