AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
19min chapter
Sholto Douglas & Trenton Bricken - How to Build & Understand GPT-7's Mind
Dwarkesh Podcast
Exploring Responsible Scaling Policy and Model Interpretability in GPT-7 Training
The chapter dives into the responsible scaling policy adopted by a lab and the challenges surrounding GPT-7's evaluation and interpretability progress. Discussions on labeling features in unsupervised manners, searching for deception circuits, and scaling up dictionary learning within a six-month timeframe showcase the team's optimism and progress. The dialogue also delves into understanding advanced AI systems like GPT-7's mind, potential risks of control, and the importance of transparent governance in shaping AI program performance.
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