What Is Depression Anyway: The Synapse Hypothesis by Scott Alexander – Six seemingly distinct treatments for depression. How at least six can be explained by considering synapse generation rates. Skepticism that this method can be used to explain anything since the body is so inter-connected. Six points that confuse Scott and deserve more research. Very technical.
Deep Reinforcement Learning From Human Preferences by Dario Amodei, Paul Christiano & Alex Ray (Open Ai) – An algorithm learns to backflip with 900 bits of feedback from the human evaluator. “One step towards building safe AI systems is to remove the need for humans to write goal functions, since using a simple proxy for a complex goal, or getting the complex goal a bit wrong, can lead to undesirable and even dangerous behavior. In collaboration with DeepMind’s safety team, we’ve developed an algorithm which can infer what humans want by being told which of two proposed behaviors is better.”
The Rationalist-sphere And The Less Wrong Wiki by Deku-shrub (lesswrong) – What’s next for the Lesswrong wiki. A distillation of Lesswrong. Fully indexing the diaspora. A list of communities. Spreading rationalist ideas. Rationalist Research.
Persona 5 Spoiler Free Review by Zvi Moshowitz – Persona games are long but deeply worthwhile if you enjoy the gameplay and the story. Persona 5 is much more polished but Persona 3 has a more meaningful story and more interesting decisions. Tips for Maximum Enjoyment of Persona 5. Very few spoilers.
The World Desperately Needs Ai Strategists: Heres How To Become One by 80,000 Hours – 80K hours released a detailed guide to careers in AI policy. ” We discuss the main career paths; what to study; where to apply; how to get started; what topics are most in need of research; and what progress has been made in the field so far.” Transcript included.