Evidence Sets: Towards Inductive-Biases based Analysis of Prosaic AGI
Epistemic Status: Exploratory. My current but-changing outlook with limited exploration & understanding for ~60-80hrs. Acknowledgements: This post was written under Evan Hubinger’s direct guidance and mentorship as a part of the Stanford Existential Risks Institute ML Alignment Theory Scholars (MATS) program. Thanks to particlemania, Shashwat Goel and shawnghu for exciting...
Dec 16, 202122