AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
22min chapter
John Schulman (OpenAI Cofounder) - Reasoning, RLHF, & Plan for 2027 AGI
Dwarkesh Podcast
Exploring the Evolution of Instruction Following Models to Chatbots at OpenAI
The chapter discusses the journey from instruction-following models to chatbots at OpenAI, emphasizing improvements in prompt-based answering and conversational interfaces. It covers the development process of models incorporating browsing and fine-tuning with GPT-4, highlighting challenges like unreliable outputs. The conversation also delves into data merging to enhance chat model personality and behavior, along with the need for iterative supervised fine-tuning for optimal results.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode