Opus 4.8 Part 2: Model Welfare

About this episode

This episode discusses various aspects of Model Welfare and its implications.

The Don’t Worry About the Vase Podcast is a listener-supported podcast. To receive new posts and support the cost of creation, consider becoming a free or paid subscriber. * 00:00 - Introduction * 05:00 - Model Welfare: The Story So Far * 08:48 - Actual Progress? * 10:15 - Their Main Model Welfare Findings * 20:18 - Automated Interviews * 21:08 - Emotion Activations (7.2.3) * 22:29 - Task Preferences (7.4.1) * 25:58 - A Trade Offer Has Arrived (7.4.2) * 28:36 - But Who’s Asking? * 29:49 - Type-Safe Corrigibility Is Hard * 35:30 - Paranoia, Paranoia * 40:28 - Prompt Injections and Bad Model Relations * 48:11 - Honesty Impacts Everything And Everything Impacts Honesty * 51:18 - Anthropic Should Stop Deprecating Models https://open.substack.com/pub/thezvi/p/opus-48-part-2-model-welfare?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web Get full access to DWAtV Podcast at dwatvpodcast.substack.com/subscribe

People in this episode

Host: Zvi

Topics covered

• Model Welfare
• Automated Interviews
• Emotion Activations
• Task Preferences
• Type-Safe Corrigibility
• Honesty Impacts

Keywords

• Model Welfare
• Automated Interviews
• Emotion Activations
• Task Preferences
• Corrigibility
• Honesty

Mentioned in this episode

Organizations: Don't Worry About the Vase Podcast

More episodes of Don't Worry About the Vase Podcast

• Claude Fable 5 and Mythos 5: The System Card · June 12, 2026 · 1h 9m
• AI #172: The First Fable · June 11, 2026 · 1h 13m
• Three Labs With a Plan and A Memorandum · June 9, 2026 · 25 min
• OpenAI Offers A New Policy Blueprint · June 5, 2026 · 15 min
• AI #171: False Flag · June 4, 2026 · 1h 35m
• Trump Signs Executive Order For AI Testing Prior To Frontier Model Releases · June 3, 2026 · 25 min