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.
This has been an Askwho Casts audio conversion. If you would like your own private feed of audio conversions of any blog posts you would like to listen to, You can sign up For Askwho Casts Pro at https://app.askwhocasts.com/, Where you can give any post the multi-voiced podcast treatment, into your own podcast feed. Thanks for listening.
00:00 - Introduction
02:23 - Executive Summary of Their Executive Summary
04:34 - RSP Evaluations (2)
11:14 - Alignment Risk Update (2.4)
12:02 - Cyber (3)
16:44 - Safeguard Robustness (3.5)
19:01 - Mundane Safeguards and Harmlessness (4)
21:10 - Agentic Safety (5)
23:37 - Prompt Injection Is Approaching Solved
26:31 - The Remaining Problem With Prompt Injections Is The Classifiers
27:16 - Alignment (6)
27:49 - Key Reported Findings (6.1.2)
31:56 - Oh My Lord Training Environments Had Some Issues (6.3.2)
34:19 - Potential Blind Spots of Our Automated Behavioral Audit (6.4.1)
35:34 - Automated Alignment Test Results (6.4.2)
38:14 - Honesty
39:34 - White Box Analysis (6.6.1)
41:18 - Scheduling Going Forward
