InstructGPT
OpenAI model family used in mirage predictions
Episodes
-
#6110: The Chatbot OpenAI Almost ShelvedInstruction models existed for months. Then a rumour about Anthropic pushed OpenAI to ship a chat box in two weeks. -
#5945: How a Reward Model Actually Trains an LLMOne number, no gradients, four models in the room. What a reward model actually does inside the RLHF loop. -
#5442: When Do LLMs Suddenly Get Good at Things?New capabilities seem to appear out of nowhere as models scale. Whether that's real — or just how we measure — is still an open fight. -
#1111: Surviving the arXiv Deluge: Finding Signal in AI's Paper FirehoseDiscover the unsung research papers that built the AI era and learn how to navigate the relentless flood of new machine learning breakthroughs.