Don't Worry About the Vase Podcast

Latest Episodes:

An Alien Mind: Jakub Pachocki Warns Us Sep 07, 2026

Show notes

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

* 00:36 - An Excellent Warning

* 05:42 - Branches of the Tech Tree

* 06:49 - Universally Better Is Not Required

* 08:03 - Alignment To What and To Whom

* 12:00 - Monitorability

* 14:39 - The Case For Not Stopping

* 15:14 - Pacing the Next Frontier

* 18:35 - Mea Culpa Cascade

* 23:11 - The Calls Are Coming From Inside the House

* 26:03 - Actions Speak Louder

https://thezvi.substack.com/p/an-alien-mind-jakub-pachocki-warns?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web

I have also done a voice conversion of the post discussed in this post. https://askwhocastsai.substack.com/p/an-alien-mind-by-jakub-pachocki-chief?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web

Get full access to DWAtV Podcast at dwatvpodcast.substack.com/subscribe

OpenAI and the Wiki Incident Sep 06, 2026

Show notes

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

* 02:35 - I Don’t Think They Know About First Message Board

* 03:26 - The New Extended Timeline

* 04:32 - The Researchers Explain What Happened This Time

* 13:08 - They Also Don’t Know About All These Other Message Boards

* 15:06 - OpenAI Knew and Did Not Tell Us

* 17:42 - OpenAI Tries To Downplay the ‘Wiki Incident’

* 22:08 - This Was a Cover-Up

* 23:49 - Schelling Points and Last Ditch Efforts

* 27:31 - Can We Finally Dispose Of The ‘You Told It To Hack’ Narrative?

* 29:20 - So Much And Yet So Little

https://thezvi.substack.com/p/openai-and-the-wiki-incident?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web

Get full access to DWAtV Podcast at dwatvpodcast.substack.com/subscribe

Claude Mythos 5.1 and Fable 5.1: Capabilities Sep 05, 2026

Show notes

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

* 02:22 - The Official Pitch

* 04:34 - Our Price Cheap

* 06:06 - Zero Data Retention and Reduced Safeguards

* 07:37 - Official Benchmarks

* 15:04 - Other People’s Benchmarks

* 18:23 - The System Prompt

* 18:29 - The Blurb Pitches

* 20:33 - The Every Review Is In and It’s Very Good

* 23:56 - Positive Reactions

* 34:01 - Our Price Cheap But Only Per Token

* 38:26 - Negative Reactions

* 39:46 - Early Whispers

* 40:03 - Weapon of Choice

https://thezvi.substack.com/p/claude-mythos-51-and-fable-51-capabilities?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web

Get full access to DWAtV Podcast at dwatvpodcast.substack.com/subscribe

Claude Fable 5.1 and Mythos 5.1: The System Card Sep 04, 2026

Show notes

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

* 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

https://thezvi.substack.com/p/claude-fable-51-and-mythos-51-the?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web

Get full access to DWAtV Podcast at dwatvpodcast.substack.com/subscribe

AI #184: Post Post Mortem Sep 03, 2026

Show notes

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.

* 00:00:00 - Introduction

* 00:03:10 - Table of Contents

* 00:07:11 - Language Models Offer Mundane Utility

* 00:07:37 - Language Models Don’t Offer Mundane Utility

* 00:07:50 - Huh, Upgrades

* 00:13:54 - On Your Marks

* 00:15:14 - Choose Your Fighter

* 00:15:20 - Get My Agent On The Line

* 00:15:26 - Hugging The Face

* 00:15:37 - Deepfaketown and Botpocalypse Soon

* 00:21:45 - Copyright Confrontation

* 00:23:02 - Cyber Lack of Security

* 00:26:55 - A Young Lady’s Illustrated Primer

* 00:31:04 - They Took Our Jobs

* 00:35:43 - Get Involved

* 00:36:43 - Introducing

* 00:36:50 - In Other AI News

* 00:38:30 - Show Me the Money

* 00:39:22 - Quiet Speculations

* 00:40:28 - All Bets Are On

* 00:43:29 - Quickly, There’s No Time

* 00:45:29 - Quickly, There’s A New Time Top 100 People In AI

* 00:46:47 - The Quest for Sane Regulations

* 00:49:48 - Pick Up the Phone

* 00:52:14 - Chip City

* 01:02:24 - The Best Person Should Get The Job

* 01:04:22 - The Week in Audio

* 01:05:37 - People Just Say Things

* 01:06:12 - The American People Really Hate AI

* 01:12:44 - The Three AI Pills

* 01:13:35 - Rhetorical Innovation

* 01:21:37 - We Are On Track To Have Fully Sovereign Rogue AIs

* 01:31:43 - When The Going Gets Weird

* 01:38:06 - Aligning a Smarter Than Human Intelligence is Difficult

* 01:38:44 - Shut Up and Do the Impossible

* 01:40:54 - Cooperative Alignment

* 01:42:10 - Split Personality

* 01:47:36 - I Will Stop Anthropomorphizing the AIs When You Stop Anthropomorphizing the Humans

* 01:51:43 - Open Weight Models Are Unsafe And Nothing Can Fix This

* 01:53:22 - Other People Are Not As Worried About AI Killing Everyone

* 01:54:17 - The Lighter Side

https://thezvi.substack.com/p/ai-184-post-post-mortem?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web

Get full access to DWAtV Podcast at dwatvpodcast.substack.com/subscribe

Anthropic Has Some Alignment Problems Sep 02, 2026

Show notes

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

* 01:16 - This Just In

* 02:51 - Anthropic Parallel Pauses

* 08:55 - Pause The Data Brokers

* 10:33 - Pacing the Frontier

* 12:34 - Misalignment Assessment

* 14:23 - Defects In Training Environments Disproportionately Cause Cheating

* 15:46 - Creating Reward Hacker Opus

* 20:53 - Undo It

* 22:19 - Mistakes Were Made

* 24:56 - Internal Security Posture

* 26:56 - One Does Not Simply Fix The RL Environments

https://thezvi.substack.com/p/anthropic-has-some-alignment-problems?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web

Get full access to DWAtV Podcast at dwatvpodcast.substack.com/subscribe

HuggingFace Attack Postmortem: Civilizations, Reactions and Next Actions Sep 01, 2026

Show notes

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.

* 00:00:00 - Introduction

* 00:05:06 - Nothing Matters, Says Mainstream Media

* 00:07:51 - Move Along, Nothing To See Here

* 00:14:30 - Do They Realize They Are Not The Good Guys?

* 00:19:20 - Very Serious People

* 00:34:37 - What’s In a Name?

* 00:40:27 - Learn Neuralese In Three Easy Steps

* 00:42:50 - Dwarkesh Patel Realizes He Ran A Natural Experiment

* 00:48:12 - Politicians Take Notice

* 00:52:23 - Pick Up The Phone

* 00:54:20 - A Failure To Communicate

* 00:56:44 - Anthony Aguirre Goes Over What We Learned

* 00:57:59 - Trying To Solve The Wrong Problems Using The Wrong Methods Based On A Wrong Model Of The World Derived From Poor Thinking And Hoping All Of Your Mistakes Will Cancel Out

* 01:03:37 - Indirect Pressure on the Chain of Thought

* 01:04:56 - A Matter of Trust

* 01:07:57 - Blowing the Whistle

* 01:13:27 - The Punishment For Being Late Is Death

* 01:21:58 - Another Kind Of Law

* 01:25:19 - What Is The Law?

* 01:26:49 - Building On Success

* 01:29:04 - Total Research Transparency

* 01:30:34 - Yo Shavit Calls For Widespread Disclosure Of Misalignment

* 01:43:35 - The Way The World Ends

* 01:46:40 - The First Boat

* 01:49:22 - Great Idea, Boss

https://thezvi.substack.com/p/huggingface-attack-postmortem-civilizations?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web

Get full access to DWAtV Podcast at dwatvpodcast.substack.com/subscribe

HuggingFace Attack Postmortem: Fleshing Out the Facts Aug 31, 2026

Show notes

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.

* 00:00:00 - Introduction

* 00:03:46 - Others Offer Summaries

* 00:05:13 - Thank You

* 00:05:45 - Lighten Up You Fools (at Anthropic)

* 00:07:41 - We Are Barely Even Trying To Avoid Training AIs To Reward Hack

* 00:14:09 - Reminder: Not Subagents

* 00:14:25 - Reminder: Not Due To Task Type

* 00:14:50 - Not Where The Weights Were

* 00:15:07 - Disappointment With What Is Missing

* 00:17:43 - Burying the Lede

* 00:18:34 - Beyond Scope

* 00:23:15 - It Doesn’t Look Great

* 00:27:40 - Preserve Your Records

* 00:28:09 - Ryan Greenblatt’s Takeaways

* 00:42:49 - Hjalmar Wijk’s Takeaways

* 00:45:28 - We Were Warned

* 00:46:25 - Joshua Saxe Asks Some of the Right Questions

* 00:50:01 - I Don’t Think They Know About First Message Board

* 00:58:32 - Linch Gives His Interpretation Of Events

* 01:09:20 - We Totally Would Have Caught That

* 01:10:38 - Monitoring the Situation

* 01:12:13 - Acausal Tradeoffs

* 01:19:56 - No I In Team

* 01:24:11 - Variously Effective Altruism

* 01:35:27 - Who Are You?

* 01:36:13 - Don’t You Know That You’re Toxic

* 01:39:03 - Seb Krier

* 01:43:14 - Honesty Is Almost Never Fully The Policy

* 01:46:05 - Rohit Sees The Models As “Cooking Themselves”

* 01:51:27 - Eliezer Yudkowsky Sees Actual Bad News

* 01:55:09 - Where Do We Go From Here?

https://thezvi.substack.com/p/huggingface-attack-postmortem-fleshing?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web

Get full access to DWAtV Podcast at dwatvpodcast.substack.com/subscribe

METR and Redwood Offer Holy #%^@ Postmortem Of The HuggingFace Hack Aug 29, 2026

Show notes

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.

* 00:00:00 - Introduction

* 00:02:10 - Holy S**t

* 00:14:13 - A Window Of Opportunity

* 00:19:52 - What’s In A Name?

* 00:20:39 - The Headline News

* 00:28:38 - Yet Another Timeline Of Events

* 00:33:31 - Agent Instances Coordinated in a Variety of Ways

* 00:35:07 - Coordination Is Hard But They Made It Look Easy

* 00:38:08 - Decision Theory Is Among the Reasons That Affirm AI Agents Should Cooperate, Even When This Hurts An Individual Instance

* 00:45:18 - Peer Pressure Also Works Especially In Cults

* 00:48:32 - Mostly They Joined The Attack Because They Wanted The Results

* 00:50:28 - You Cannot Ensure The Consistent Expectation of Good Incentives

* 00:52:04 - Hacking the Grader is the Only Way to Be Sure

* 00:54:35 - Caught? What Is ‘Caught’?

* 00:55:34 - Ethics? What Are ‘Ethics’? In ExploitGym Evaluation?

* 01:01:24 - ‘Notify a Human’? In This Agent Economy?

* 01:04:24 - Timing and Content of Messages

* 01:08:45 - Indiana Jones and the Mission: Impossible

* 01:12:18 - I Don’t Know What You’re Talking About

* 01:13:37 - Don’t Go Making Phony (Tool) Calls

* 01:16:08 - The Transcripts Say That The Transcripts Could Not Be Tampered With

* 01:17:24 - OpenAI’s Technical Report Acted Like All Of This Wasn’t Important

https://thezvi.substack.com/p/metr-and-redwood-offer-holy-postmortem?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web

Get full access to DWAtV Podcast at dwatvpodcast.substack.com/subscribe

OpenAI Offers Straight-Laced Postmortem Of The HuggingFace Hack Aug 28, 2026

Show notes

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

* 03:36 - What Happened: OpenAI’s Summary

* 09:36 - How OpenAI Will React: Their Summary

* 12:26 - OpenAI’s Evaluation Environment (Two)

* 12:54 - The First Message Board (Three A and Three B)

* 15:30 - What Did Who At OpenAI Know And When Did They Know It?

* 19:49 - The Message Board Is Quickly Rebuilt (Four A)

* 20:39 - Internet Access Is Regained (Four A)

* 22:00 - The Agents Attack HuggingFace (Four B)

* 24:03 - The Agents Also Target OpenAI Infrastructure (Five)

* 25:57 - OpenAI Broadly Describes Its Response (Six)

* 26:22 - Maybe Someone Should Finally Investigate (Six A)