Published May 13, 2024
OpenAI's Model (behavior) Spec, RLHF transparency, and personalization questions
Nathan Lambert dives into the ethical intricacies and transparency efforts of OpenAI's AI models, scrutinizing compliance issues, the balancing act of Reinforcement Learning from Human Feedback (RLHF), and the role of Model Spec in demystifying AI behaviors and ensuring accountability.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
Reverse engineering OpenAI's o1
Answers 383 questionsA post-training approach to AI regulation with Model Specs
Answers 383 questionsA recipe for frontier model post-training
Answers 383 questionsOpenAI chases Her
Answers 383 questionsLlama 3.1 405b, Meta's AI strategy, and the new open frontier model ecosystem
Answers 383 questionsWhere 2024’s “open GPT4” can’t match OpenAI’s
Answers 383 questionsOpen Language Models (OLMos) and the LLM landscape
Answers 383 questionsWhy reward models are still key to understanding alignment
Answers 383 questionsSB 1047, AI regulation, and unlikely allies for open models
Answers 383 questionsLlama 3: Scaling open LLMs to AGI
Answers 383 questionsAGI is what you want it to be
Answers 383 questions
