Results for "token efficiency"
Keyword scan across titles, descriptions, summaries, and tags. For interview listings, try Guest appearances.
2 results
Episodes
StandardSummaries only[State of Post-Training] From GPT-4.1 to 5.1: RLVR, Agent & Token Efficiency — Josh McGrath, OpenAI
Latent Space: The AI Engineer Podcast· Dec 31, 2025
From pre-training data curation to shipping GPT-4o, o1, o3, and now GPT-5 thinking and the shopping model, Josh McGrath has lived through the full arc of OpenAI's post-training evolution—from the PPO vs DPO debates of 20…
openaisafety-alignment
Intelligent Report10AM Hour: OpenAI CEO Sam Altman on New Model, Palo Alto Networks CEO on AI Spending, Match Group CEO on AI & Dating 7/9/26
Squawk on the Street· Jul 9, 2026
OpenAI CEO Sam Altman unveils ChatGPT's 54% more token-efficient model, Palo Alto Networks' Nikesh Arora weighs in on AI costs, and H.R. McMaster analyzes escalating U.S.-Iran strikes.
openaiinvesting