Alexandr Wang
The Robot Brains Podcast
Alexandr Wang: data, foundation models, RLHF, AI for defense
- Published
- March 29, 2023
- Duration
- 1h 3m
- Summary source
- description
- Last updated
- Jun 10, 2026
Discusses safety-alignment.
Summary
Alexandr Wang from Scale AI joins Host Pieter Abbeel to discuss data, labeling, foundation models, LLMs, truthfulness, reinforcement learning from human feedback (RLHF), and AI for defense.SUBSCRIBE TO THE ROBOT BRAINS PODCAST TODAY | Visit therobotbrains.ai and follow us on YouTube at TheRobotBrainsPodcast andTwitter @therobotbrains. Hosted on Acast. See…
Intelligent report
Sign in to read teasers, or upgrade to Research Pro to commission a new dossier for this episode. Learn more →
Show notes
Alexandr Wang from Scale AI joins Host Pieter Abbeel to discuss data, labeling, foundation models, LLMs, truthfulness, reinforcement learning from human feedback (RLHF), and AI for defense.SUBSCRIBE TO THE ROBOT BRAINS PODCAST TODAY | Visit therobotbrains.ai and follow us on YouTube at TheRobotBrainsPodcast andTwitter @therobotbrains. Hosted on Acast. See acast.com/privacy for more information.
Themes
- safety-alignment