Three Questions that Keep Me Up at Night | Eric Jang

Q1: Can we imitate “thinking” from only observing behavior?

Q1: Can we imitate "thinking" from only observing behavior? Suppose you have a large fleet of autonomous vehicles with human operators driving them around diverse road conditions. We can observe the decisions made by the human, and attempt to use imitation learning algorithms to map robot observations to the steering decisions that the human would take. However, we can't observe what the homunculus is thinking directly. Humans read road text and other signage to interpret what they should and should not do. Humans plan more carefully when doing tricky maneuvers (parallel parking). Humans feel

related reading

• Andrej Karpathy — AGI is still a decade awaydwarkesh.com
• The Artificial Intelligence Revolution: Part 1 - Wait But Whywaitbutwhy.com
• [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
• The Era of Experience Paper.pdfstorage.googleapis.com
• [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
• Cyborgism — LessWronglesswrong.com
• State of Robot Learning, December 2025vedder.io
• alan turing - computing machinery and intelligencecourses.cs.umbc.edu
• Forms of life, forms of mind | Dr. Michael Levin | Algorithms Redux: finding unexpected properties in truly minimal systemsthoughtforms.life
• Building machines that learn and think like people | Behavioral and Brain Sciences | Cambridge Corecambridge.org
• Fully autonomous robots are much closer than you think – Sergey Levinedwarkesh.com
• 9 Open Problems and Directions about Intelligencema-lab-berkeley.github.io