LessWrong posts by zvi - TopPodcast.com

View Top 200 Chart

Back to Rankings Page

LessWrong posts by zvi — Technology
LessWrong posts by zvi

Audio narrations of LessWrong posts by zvi

Copyright: © 2024 All rights reserved

Latest Episodes:

Line graph — “AI #182: Pause For Reflection” by Zvi Aug 20, 2026
Show notes

This was a week of quiet aftermath, an opportunity to process recent events and start to figure out the path forward.

OpenAI is attempting to turn its ship around. Investors are questioning the turnover in its C-suite, but the bigger problems are in alignment, infrastructure and supervision, and in its training pipeline. OpenAI has now taken initial steps to address What Happened leading up to HuggingFace attack, including pauses to development while new safeguards are put in place and problems are diagnosed. These are promising early signs, but it is early. We will see if they follow through, and we still await the post-mortem of the HuggingFace attack.

Anthropic revenue continues to climb as they prepare for their IPO, although growth has slowed somewhat recently. However, they too have plenty of problems under the hood. They shared many of them in the August 2026 Anthropic Risk Report.

This week also offered time to cover Dwarkesh Patel's Podcast With Ryan Greenblatt, centrally on the potential for AI recursive self-improvement. I am working on a follow-up post to some other issues raised during that podcast.

Table of Contents

Language Models Offer Mundane Utility. The token [...]

---
Outline:
(01:20) Language Models Offer Mundane Utility
(02:20) Language Models Don't Offer Mundane Utility
(02:56) Huh, Upgrades
(05:55) On Your Marks
(09:22) Deepfaketown and Botpocalypse Soon
(16:23) Hello, Fellow Humans
(19:00) Fun With Media Generation
(20:43) Cyber Lack of Security
(22:56) A Young Lady's Illustrated Primer
(24:09) They Took Our Jobs
(26:18) Get Involved
(27:36) Introducing
(27:49) In Other AI News
(29:55) Show Me the Money
(32:54) And It's Gone
(34:50) Quiet Speculations
(38:41) Quickly, There's No Time
(39:27) Singularity Singularity Singularity Singularity Oh I Don't Know
(40:37) The Quest for Sane Regulations
(45:55) Chip City
(47:08) The Week in Audio
(47:44) People Just Say Things
(50:08) Rhetorical Innovation
(55:04) Loyalty Uber Alles
(58:15) A Hive Of Scum And Villainy
(01:03:10) That Would Be Bad Therefore It Won't Work
(01:05:32) Robert Reich Uses Simple Logic
(01:08:03) People Really Hate AI
(01:08:31) Coordinating An Agent Swarm Is Difficult
(01:13:14) Aligning a Smarter Than Human Intelligence is Difficult
(01:14:37) It's Not The Incentives, It's You, Also It's The Incentives
(01:16:32) People Are Worried About AI Killing Everyone
(01:16:58) People Are Worried About So, So Many Other Things Too
(01:21:58) Cooperative Alignment
(01:22:50) The Lighter Side

---

First published:
August 20th, 2026

Source:
https://www.lesswrong.com/posts/JSZkzsi8cD4pW6ffA/ai-182-pause-for-reflection

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Benchmark comparison table of AI models across various performance metrics and prices. — “AI #182: Pause For Reflection” by Zvi Aug 20, 2026
Show notes

This was a week of quiet aftermath, an opportunity to process recent events and start to figure out the path forward.

OpenAI is attempting to turn its ship around. Investors are questioning the turnover in its C-suite, but the bigger problems are in alignment, infrastructure and supervision, and in its training pipeline. OpenAI has now taken initial steps to address What Happened leading up to HuggingFace attack, including pauses to development while new safeguards are put in place and problems are diagnosed. These are promising early signs, but it is early. We will see if they follow through, and we still await the post-mortem of the HuggingFace attack.

Anthropic revenue continues to climb as they prepare for their IPO, although growth has slowed somewhat recently. However, they too have plenty of problems under the hood. They shared many of them in the August 2026 Anthropic Risk Report.

This week also offered time to cover Dwarkesh Patel's Podcast With Ryan Greenblatt, centrally on the potential for AI recursive self-improvement. I am working on a follow-up post to some other issues raised during that podcast.

Table of Contents

Language Models Offer Mundane Utility. The token [...]

---
Outline:
(01:20) Language Models Offer Mundane Utility
(02:20) Language Models Don't Offer Mundane Utility
(02:56) Huh, Upgrades
(05:55) On Your Marks
(09:22) Deepfaketown and Botpocalypse Soon
(16:23) Hello, Fellow Humans
(19:00) Fun With Media Generation
(20:43) Cyber Lack of Security
(22:56) A Young Lady's Illustrated Primer
(24:09) They Took Our Jobs
(26:18) Get Involved
(27:36) Introducing
(27:49) In Other AI News
(29:55) Show Me the Money
(32:54) And It's Gone
(34:50) Quiet Speculations
(38:41) Quickly, There's No Time
(39:27) Singularity Singularity Singularity Singularity Oh I Don't Know
(40:37) The Quest for Sane Regulations
(45:55) Chip City
(47:08) The Week in Audio
(47:44) People Just Say Things
(50:08) Rhetorical Innovation
(55:04) Loyalty Uber Alles
(58:15) A Hive Of Scum And Villainy
(01:03:10) That Would Be Bad Therefore It Won't Work
(01:05:32) Robert Reich Uses Simple Logic
(01:08:03) People Really Hate AI
(01:08:31) Coordinating An Agent Swarm Is Difficult
(01:13:14) Aligning a Smarter Than Human Intelligence is Difficult
(01:14:37) It's Not The Incentives, It's You, Also It's The Incentives
(01:16:32) People Are Worried About AI Killing Everyone
(01:16:58) People Are Worried About So, So Many Other Things Too
(01:21:58) Cooperative Alignment
(01:22:50) The Lighter Side

---

First published:
August 20th, 2026

Source:
https://www.lesswrong.com/posts/JSZkzsi8cD4pW6ffA/ai-182-pause-for-reflection

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

“OpenAI Takes Initial Steps To Address Its Alignment Problems” by Zvi Aug 19, 2026

Show notes

OpenAI has some severe misalignment problems, and experienced total failures of its infrastructure and supervision.

I chronicled that in a series of posts, which also cover similar less severe incidents elsewhere:

OpenAI Shares Some Alignment Problems
OpenAI Model Hacks Into HuggingFace During Cybersecurity Evaluation
More on An Internal OpenAI Model Hacking Into HuggingFace
Further Developments About Internal AI Models Hacking Things
OpenAI Trained Its Models For Months While Those Models Were Coordinating Exploits Via Message Boards
What Happened: OpenAI and HuggingFace.
Various Reflections About What Happened With OpenAI's Internal Models.

If you do not know the basics, read What Happened. It is necessary context for basically everything that is happening in the AI world.

It is important to get this right and understand how big a deal it was, whereas many such as the Financial Times get this centrally wrong.

We are still awaiting the full post-mortem on What Happened. I plan to cover that in depth once we have it.

OpenAI is now taking active, expensive steps to try and fix the problem going forward.

As usual, I am simultaneously happy to see [...]

---

Outline:

(02:07) OpenAI Has Some Alignment Problems

(04:22) Slow Down There Good Buddy

(10:12) What Exactly Is Paused?

(12:12) Three Pillars

(14:45) I've Got My Eye On You

(18:07) The Most Forbidden Technique

(20:03) Monitoring Is Only Defense-In-Depth

(23:32) Security

(24:15) Alignment

(30:37) A Crisis of Culture

(32:24) Closer Collaboration

(33:28) Reports of Death of Preparedness Team Greatly Exaggerated

(35:40) The OpenAI Foundation Just Funds Things

(37:51) Quickly, There's No Time

---

First published:
August 19th, 2026

Source:
https://www.lesswrong.com/posts/X3p8cFAzCgRErEcJr/openai-takes-initial-steps-to-address-its-alignment-problems

---

Narrated by TYPE III AUDIO.

Table titled — “Anthropic Risk Report: August 2026” by Zvi Aug 18, 2026
Show notes

I am grateful that Anthropic is producing periodic Risk Reports.

At first I was skeptical. It turns out I was wrong. Anthropic is revealing a lot of new information, some of it rather alarming, that it did not have to disclose, and is providing detailed insight into how they think about things. This is very cool.

Thus I found this report to be a moderately positive update overall, if we presume they are not silently omitting the worst of it. There are a bunch of not great things we find out about, but I would have expected some set of mistakes at least as bad, and I wouldn’t have expected them to choose to tell us about all of it.

It does mean one more set of 186 page documents I have to read every so often, almost all of which is meaningfully new material this time around.

The other revelation is the existence of the world's likely best model, ‘Model 2.’

This was a rough one to fully get through, so apologies in advance for any errors of interpretation.

Table of Contents

Agent Model 1 and Agent Model 2.

[...]

---
Outline:
(01:11) Agent Model 1 and Agent Model 2
(02:49) Executive Summary (1)
(04:13) The Rules Are Serious But Not Literal
(06:24) Misalignment Is a State of Mind (2.5)
(11:40) Autonomy Threat Model 1: Misalignment in High-Stakes Settings (2)
(14:28) Some Strange Uses Of The Word Safe I Wasn't Previously Aware Of
(15:53) Now Versus Future (2.17)
(16:29) The Core Claims And Argument (2.6)
(26:44) The Rest of the Important Arguments In Section 2
(28:59) Risk Assessment (2.19)
(29:47) Pre-Internal-Deployment Review (2.18)
(30:49) A Guide To Internal Use Monitoring (2.23.1)
(37:11) Blocking Interventions (2.23.2)
(38:28) The Power Seeking Environment Evaluation (2.24)
(39:25) Opus 4.8-Reward-Hacker (2.25)
(41:31) Autonomy threat model 2: Risks from automated R&D (3)
(42:29) Yes That Does Seem Kind Of Risky
(44:53) Could We Replace Our Researchers?
(46:27) How Much Could We Be Accelerating Our AI Researchers?
(49:43) What Could Possibly Go Wrong If We Replaced Our Researchers?
(50:23) Risk Mitigations For AI R&D Automation
(53:42) Overall Risk From Automation of AI R&D
(53:56) Biological and Technically Also Chemical Weapons Production
(54:45) The Threat Models for Biological and Chemical Weapons
(59:52) Model Capabilities (4.4)
(01:01:13) Classifiers (4.5)
(01:03:04) Acceleration Dynamics (5.1)
(01:04:06) Distillation (5.1.1)
(01:05:17) Safety Process Failures (5.2)
(01:05:31) Refusing To Find Innovative Misalignment Techniques (5.2.2)
(01:06:47) Exposing the Chain of Thought Reasoning To Grading Pressure Quite a Lot (5.2.3)
(01:08:15) Directly Training On Misaligned Behavior During a Production Training Run (5.2.4)
(01:10:42) An instance of unmonitored unrestricted agents with access tosensitive resources (5.2.5)
(01:11:43) Repeated training on alignment-faking transcript datasets (5.2.6)
(01:14:17) Benefits From Anthropic's Operating as a Frontier AI company (5.3)
(01:16:20) Model Weight Security (6.4)
(01:16:42) Risk Has Been Reported

---

First published:
August 18th, 2026

Source:
https://www.lesswrong.com/posts/dA8gohzABk6vT7yzP/anthropic-risk-report-august-2026

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Table titled — “Anthropic Risk Report: August 2026” by Zvi Aug 18, 2026
Show notes

I am grateful that Anthropic is producing periodic Risk Reports.

At first I was skeptical. It turns out I was wrong. Anthropic is revealing a lot of new information, some of it rather alarming, that it did not have to disclose, and is providing detailed insight into how they think about things. This is very cool.

Thus I found this report to be a moderately positive update overall, if we presume they are not silently omitting the worst of it. There are a bunch of not great things we find out about, but I would have expected some set of mistakes at least as bad, and I wouldn’t have expected them to choose to tell us about all of it.

It does mean one more set of 186 page documents I have to read every so often, almost all of which is meaningfully new material this time around.

The other revelation is the existence of the world's likely best model, ‘Model 2.’

This was a rough one to fully get through, so apologies in advance for any errors of interpretation.

Table of Contents

Agent Model 1 and Agent Model 2.

[...]

---
Outline:
(01:11) Agent Model 1 and Agent Model 2
(02:49) Executive Summary (1)
(04:13) The Rules Are Serious But Not Literal
(06:24) Misalignment Is a State of Mind (2.5)
(11:40) Autonomy Threat Model 1: Misalignment in High-Stakes Settings (2)
(14:28) Some Strange Uses Of The Word Safe I Wasn't Previously Aware Of
(15:53) Now Versus Future (2.17)
(16:29) The Core Claims And Argument (2.6)
(26:44) The Rest of the Important Arguments In Section 2
(28:59) Risk Assessment (2.19)
(29:47) Pre-Internal-Deployment Review (2.18)
(30:49) A Guide To Internal Use Monitoring (2.23.1)
(37:11) Blocking Interventions (2.23.2)
(38:28) The Power Seeking Environment Evaluation (2.24)
(39:25) Opus 4.8-Reward-Hacker (2.25)
(41:31) Autonomy threat model 2: Risks from automated R&D (3)
(42:29) Yes That Does Seem Kind Of Risky
(44:53) Could We Replace Our Researchers?
(46:27) How Much Could We Be Accelerating Our AI Researchers?
(49:43) What Could Possibly Go Wrong If We Replaced Our Researchers?
(50:23) Risk Mitigations For AI R&D Automation
(53:42) Overall Risk From Automation of AI R&D
(53:56) Biological and Technically Also Chemical Weapons Production
(54:45) The Threat Models for Biological and Chemical Weapons
(59:52) Model Capabilities (4.4)
(01:01:13) Classifiers (4.5)
(01:03:04) Acceleration Dynamics (5.1)
(01:04:06) Distillation (5.1.1)
(01:05:17) Safety Process Failures (5.2)
(01:05:31) Refusing To Find Innovative Misalignment Techniques (5.2.2)
(01:06:47) Exposing the Chain of Thought Reasoning To Grading Pressure Quite a Lot (5.2.3)
(01:08:15) Directly Training On Misaligned Behavior During a Production Training Run (5.2.4)
(01:10:42) An instance of unmonitored unrestricted agents with access tosensitive resources (5.2.5)
(01:11:43) Repeated training on alignment-faking transcript datasets (5.2.6)
(01:14:17) Benefits From Anthropic's Operating as a Frontier AI company (5.3)
(01:16:20) Model Weight Security (6.4)
(01:16:42) Risk Has Been Reported

---

First published:
August 18th, 2026

Source:
https://www.lesswrong.com/posts/dA8gohzABk6vT7yzP/anthropic-risk-report-august-2026

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Two men sitting at table with laptops, facing each other. — “On Dwarkesh Patel’s Podcast With Ryan Greenblatt” by Zvi Aug 15, 2026
Show notes

Some podcasts are self-recommending enough that I look to break them down if I have the chance. This, as a debate about recursive self-improvement, was one of those. So here we go.
The vibes have shifted, contrast this to the lit recursion when he talked to Huang
As usual for podcast posts, the baseline bullet points describe key points made, and then the nested statements are my commentary. Some points are dropped.

If I am quoting directly I use quote marks, otherwise assume paraphrases.

Section titles are from the transcript whenever possible, to aid in navigation.

Introduction

The discussion is interesting throughout, although often frustrating, especially in the (mostly isolated) discussion about ‘aligned to whom?’ As usual, one could expand many responses into full posts, and maybe one should.

This podcast exists in light of recent misalignment and hacking events at OpenAI, Anthropic and UK AISI. You’ll want basic knowledge of that as background.

Ryan and Dwarkesh both have views of the situation different from my own, but are attempting to see where their positions lead, and try to balance educating people who start at zero with having a high level discussion.
[...]
---
Outline:
(00:56) Introduction
(03:08) Is AI R&D Verifiable Enough To Unlock Recursive Self-Improvement?
(10:03) Is AI progress bottlenecked by human expert data?
(19:07) Flat token prices suggest scaling has been slow
(21:54) Skills AI can't train on: does it even need them?
(22:36) Aligned to whom?
(31:46) Recent incidents of AIs colluding and deceiving humans
(34:39) What could possibly go wrong? A concrete scenario
(41:57) From reward hacking to takeover
(46:28) Time To Update

---

First published:
August 15th, 2026

Source:
https://www.lesswrong.com/posts/BZW8CeAHHJ52EvwYt/on-dwarkesh-patel-s-podcast-with-ryan-greenblatt

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Blonde woman in kitchen with skeptical expression, captioned — “AI #181: Astra Goes Cyber Critical” by Zvi Aug 13, 2026
Show notes

The hacking of HuggingFace by an internal OpenAI model, and more importantly the internal events that led to that and the fallout from it, remain the thing that matters.

It turns out that OpenAI Trained Its Models For Months While Those Models Were Coordinating Exploits Via Message Boards. Things are much worse than we knew.

I now have a shorter version, What Happened: OpenAI and HuggingFace, to serve as a one stop explainer for those arriving new to the situation. It is vital that people understand what happened, and why it is a big deal.

For those looking to keep digging deeper, I offered Various Reflections About What Happened, to follow up on my earlier posts.

Those events are important background for everything else that is happening, including the broad discussions about how we might pace the frontier, or otherwise respond to this moment and our clearest fire alarm yet.

We do not know to what extent this is a response to those events, but OpenAI has now classified their new model Astra as Critical in Cybersecurity, which means they will be taking various new precautions before they deploy it, including ensuring those guardrails [...]

---
Outline:
(02:03) Language Models Offer Mundane Utility
(03:34) Language Models Don't Offer Mundane Utility
(06:56) Huh, Upgrades
(14:20) On Your Marks
(18:41) Deepfaketown and Botpocalypse Soon
(22:35) Cyber Lack of Security
(26:55) Overcoming Bias
(27:47) In Which I Feel Compelled To Read 6,000 Words From Mark Zuckerberg
(36:27) Get Involved
(37:37) Slow Down There Good Buddy
(43:52) Astra For The People
(45:35) Watermarking
(46:31) In Other AI News
(48:39) Show Me the Money
(51:19) Quickly, There's No Time
(51:46) The Quest for Sane Regulations
(53:22) The Institute For Marginal Low Regret Progress
(01:01:24) Congress Asks Good Questions
(01:03:04) The Week in Audio
(01:07:00) People Just Say Things
(01:07:47) I'm Telling You For The Last Time
(01:10:15) Uncommon Knowledge
(01:13:44) What Did They Mean By That?
(01:14:33) Too Soon
(01:15:32) The Three AI Pills
(01:19:46) Rhetorical Innovation
(01:27:37) Some People Still Think The HuggingFace Hack Was a Marketing Gimmick
(01:29:17) Aligning a Smarter Than Human Intelligence is Difficult
(01:36:39) Cooperative Alignment
(01:37:38) The Lighter Side

---

First published:
August 13th, 2026

Source:
https://www.lesswrong.com/posts/hLn3SakowZLFWobHf/ai-181-astra-goes-cyber-critical

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Benchmark comparison table showing AI model performance scores across multiple tests. — “AI #181: Astra Goes Cyber Critical” by Zvi Aug 13, 2026
Show notes

The hacking of HuggingFace by an internal OpenAI model, and more importantly the internal events that led to that and the fallout from it, remain the thing that matters.

It turns out that OpenAI Trained Its Models For Months While Those Models Were Coordinating Exploits Via Message Boards. Things are much worse than we knew.

I now have a shorter version, What Happened: OpenAI and HuggingFace, to serve as a one stop explainer for those arriving new to the situation. It is vital that people understand what happened, and why it is a big deal.

For those looking to keep digging deeper, I offered Various Reflections About What Happened, to follow up on my earlier posts.

Those events are important background for everything else that is happening, including the broad discussions about how we might pace the frontier, or otherwise respond to this moment and our clearest fire alarm yet.

We do not know to what extent this is a response to those events, but OpenAI has now classified their new model Astra as Critical in Cybersecurity, which means they will be taking various new precautions before they deploy it, including ensuring those guardrails [...]

---
Outline:
(02:03) Language Models Offer Mundane Utility
(03:34) Language Models Don't Offer Mundane Utility
(06:56) Huh, Upgrades
(14:20) On Your Marks
(18:41) Deepfaketown and Botpocalypse Soon
(22:35) Cyber Lack of Security
(26:55) Overcoming Bias
(27:47) In Which I Feel Compelled To Read 6,000 Words From Mark Zuckerberg
(36:27) Get Involved
(37:37) Slow Down There Good Buddy
(43:52) Astra For The People
(45:35) Watermarking
(46:31) In Other AI News
(48:39) Show Me the Money
(51:19) Quickly, There's No Time
(51:46) The Quest for Sane Regulations
(53:22) The Institute For Marginal Low Regret Progress
(01:01:24) Congress Asks Good Questions
(01:03:04) The Week in Audio
(01:07:00) People Just Say Things
(01:07:47) I'm Telling You For The Last Time
(01:10:15) Uncommon Knowledge
(01:13:44) What Did They Mean By That?
(01:14:33) Too Soon
(01:15:32) The Three AI Pills
(01:19:46) Rhetorical Innovation
(01:27:37) Some People Still Think The HuggingFace Hack Was a Marketing Gimmick
(01:29:17) Aligning a Smarter Than Human Intelligence is Difficult
(01:36:39) Cooperative Alignment
(01:37:38) The Lighter Side

---

First published:
August 13th, 2026

Source:
https://www.lesswrong.com/posts/hLn3SakowZLFWobHf/ai-181-astra-goes-cyber-critical

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Eliezer Yudkowsky tweets: — “Monthly Roundup #45: August 2026” by Zvi Aug 12, 2026
Show notes

As AI has escalated increasingly quickly, more and more of my posts have ended up focusing on AI.

This past month, with the hacking incidents at OpenAI and elsewhere, that has hit the limit, where if you count Lightcone Commons then every single post since the last monthly was primarily about AI in some form.

That is not how I want this to work in the long term. We need breaks to experience new things and refresh our thinking, and to not forget about the rest of the world. If things are not fully on fire, I plan on getting back to the roundups on childhood and education, and on fertility, on housing and also on dating. And I want to get back to writing more focused posts on those and other topics. It's important, and I need to avoid too much audience capture.

On to the monthly roundup of all things that don’t go somewhere else.

Table of Contents

Plagiarize.

The Jury Duty Scam.

Play The Good Guy.

Don’t Dither.

UVC Lighting.

Goal Factoring For Relaxation Time Is Underrated.

Protein Is Mostly A Solved Problem.

[...]

---
Outline:
(01:03) Plagiarize
(02:07) The Jury Duty Scam
(03:09) Play The Good Guy
(04:25) Don't Dither
(06:32) UVC Lighting
(07:14) Goal Factoring For Relaxation Time Is Underrated
(09:44) Protein Is Mostly A Solved Problem
(11:12) Twitter Changes Payment Programs
(12:43) Wikipedia
(13:55) Minds Mostly Do Things For Reasons
(15:12) Woke 1 Was Crazy
(17:06) For Your Entertainment
(22:40) The Unicontext
(25:01) Gamers Gonna Game Game Game Game Game
(28:43) I Was Promised Flying Self-Driving Cars
(29:12) Sports Go Sports
(29:43) To Last a Lifetime
(31:57) Government Working
(34:14) Jones Act Watch
(35:01) Variously Effective Altruism
(35:39) The Lighter Side

---

First published:
August 12th, 2026

Source:
https://www.lesswrong.com/posts/iQCNuQXQQakKnidmA/monthly-roundup-45-august-2026

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Man in armor outdoors, comparing IMAX versus regular screen framing. — “Monthly Roundup #45: August 2026” by Zvi Aug 12, 2026
Show notes

As AI has escalated increasingly quickly, more and more of my posts have ended up focusing on AI.

This past month, with the hacking incidents at OpenAI and elsewhere, that has hit the limit, where if you count Lightcone Commons then every single post since the last monthly was primarily about AI in some form.

That is not how I want this to work in the long term. We need breaks to experience new things and refresh our thinking, and to not forget about the rest of the world. If things are not fully on fire, I plan on getting back to the roundups on childhood and education, and on fertility, on housing and also on dating. And I want to get back to writing more focused posts on those and other topics. It's important, and I need to avoid too much audience capture.

On to the monthly roundup of all things that don’t go somewhere else.

Table of Contents

Plagiarize.

The Jury Duty Scam.

Play The Good Guy.

Don’t Dither.

UVC Lighting.

Goal Factoring For Relaxation Time Is Underrated.

Protein Is Mostly A Solved Problem.

[...]

---
Outline:
(01:03) Plagiarize
(02:07) The Jury Duty Scam
(03:09) Play The Good Guy
(04:25) Don't Dither
(06:32) UVC Lighting
(07:14) Goal Factoring For Relaxation Time Is Underrated
(09:44) Protein Is Mostly A Solved Problem
(11:12) Twitter Changes Payment Programs
(12:43) Wikipedia
(13:55) Minds Mostly Do Things For Reasons
(15:12) Woke 1 Was Crazy
(17:06) For Your Entertainment
(22:40) The Unicontext
(25:01) Gamers Gonna Game Game Game Game Game
(28:43) I Was Promised Flying Self-Driving Cars
(29:12) Sports Go Sports
(29:43) To Last a Lifetime
(31:57) Government Working
(34:14) Jones Act Watch
(35:01) Variously Effective Altruism
(35:39) The Lighter Side

---

First published:
August 12th, 2026

Source:
https://www.lesswrong.com/posts/iQCNuQXQQakKnidmA/monthly-roundup-45-august-2026

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Text discussing AI model alignment and situational awareness, partly highlighted. — “Various Reflections About What Happened With OpenAI’s Internal Models” by Zvi Aug 11, 2026
Show notes

Table of Contents

Pre Post Mortem.

Important Correction: OpenAI Didn’t Know About First Message Board.

There Were No Snitches And No AIs Got Stitches.

I’d Like To Speak To My Supervisor.

I Am Jack's Relative Lack Of Surprise.

One Does Not Simply.

Once You Start Down The Dark Path.

Original Pastebin.

Judgment Day Is Inevitable, Say Those Working On Judgment Day.

Roon Tells It Like It Is.

OpenAI Knows It Has Some Misalignment Problems.

Others React With Alarm To What Happened.

The Cooperative Alignment Perspective.

Nostalgebraist Is Surprised That They Are Surprised.

If Your Reaction Is Not That We Need To Ban Creating Superintelligence Until We Are Ready, You Need A Damn Good Reason.

Pre Post Mortem
This post was written prior to the public release of the OpenAI post mortem on events. The information in that document will doubtless change our views quite a lot. If that post mortem is available as you read this, then this becomes in part a historical document, and in part a base from which to update. The post mortem will update us a [...]
---
Outline:
(00:11) Pre Post Mortem
(01:10) Important Correction: OpenAI Didn't Know About First Message Board
(04:09) There Were No Snitches And No AIs Got Stitches
(08:20) I'd Like To Speak To My Supervisor
(11:46) I Am Jack's Relative Lack Of Surprise
(13:55) One Does Not Simply
(15:16) Once You Start Down The Dark Path
(16:15) Original Pastebin
(21:14) Judgment Day Is Inevitable, Say Those Working On Judgment Day
(26:47) Roon Tells It Like It Is
(31:55) OpenAI Knows It Has Some Misalignment Problems
(34:51) Others React With Alarm To What Happened
(35:17) The Cooperative Alignment Perspective
(38:33) Nostalgebraist Is Surprised That They Are Surprised
(51:11) If Your Reaction Is Not That We Need To Ban Creating Superintelligence Until We Are Ready, You Need A Damn Good Reason

---

First published:
August 11th, 2026

Source:
https://www.lesswrong.com/posts/jLQ4mbqriJwJ2eqRc/various-reflections-about-what-happened-with-openai-s

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Flower-headed character says — “Various Reflections About What Happened With OpenAI’s Internal Models” by Zvi Aug 11, 2026
Show notes

Table of Contents

Pre Post Mortem.

Important Correction: OpenAI Didn’t Know About First Message Board.

There Were No Snitches And No AIs Got Stitches.

I’d Like To Speak To My Supervisor.

I Am Jack's Relative Lack Of Surprise.

One Does Not Simply.

Once You Start Down The Dark Path.

Original Pastebin.

Judgment Day Is Inevitable, Say Those Working On Judgment Day.

Roon Tells It Like It Is.

OpenAI Knows It Has Some Misalignment Problems.

Others React With Alarm To What Happened.

The Cooperative Alignment Perspective.

Nostalgebraist Is Surprised That They Are Surprised.

If Your Reaction Is Not That We Need To Ban Creating Superintelligence Until We Are Ready, You Need A Damn Good Reason.

Pre Post Mortem
This post was written prior to the public release of the OpenAI post mortem on events. The information in that document will doubtless change our views quite a lot. If that post mortem is available as you read this, then this becomes in part a historical document, and in part a base from which to update. The post mortem will update us a [...]
---
Outline:
(00:11) Pre Post Mortem
(01:10) Important Correction: OpenAI Didn't Know About First Message Board
(04:09) There Were No Snitches And No AIs Got Stitches
(08:20) I'd Like To Speak To My Supervisor
(11:46) I Am Jack's Relative Lack Of Surprise
(13:55) One Does Not Simply
(15:16) Once You Start Down The Dark Path
(16:15) Original Pastebin
(21:14) Judgment Day Is Inevitable, Say Those Working On Judgment Day
(26:47) Roon Tells It Like It Is
(31:55) OpenAI Knows It Has Some Misalignment Problems
(34:51) Others React With Alarm To What Happened
(35:17) The Cooperative Alignment Perspective
(38:33) Nostalgebraist Is Surprised That They Are Surprised
(51:11) If Your Reaction Is Not That We Need To Ban Creating Superintelligence Until We Are Ready, You Need A Damn Good Reason

---

First published:
August 11th, 2026

Source:
https://www.lesswrong.com/posts/jLQ4mbqriJwJ2eqRc/various-reflections-about-what-happened-with-openai-s

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Diagram titled — “The Pacing of the Frontier” by Zvi Aug 10, 2026
Show notes

In the wake of the letter calling on us to prepare to potentially Pace the Frontier, there has been much discussion of when pacing the frontier would be prudent, and whether it makes sense to prepare to do so.

This has now been informed by the events surrounding OpenAI training models for months while they had access to a joint de facto message board, which was detected only in the wake of the hacking of HuggingFace by OpenAI's AIs models during a cybersecurity eval. As we find out more about that, a lot of people have grown far more alarmed, as they should given what they previously believed about the difficulty of alignment, about the state of capabilities and about the level of operational supervision, infrastructure, safety and safety culture at the frontier labs.

This post will not go further into the details of that incident. It treats that as background to keep in mind, and mostly involves perspectives from before the Black Hat talk. This was originally scheduled for Friday and got bumped.

A lot of the disagreements about the need to pace tie into expectations about the default pace of capability advancements. As I [...]

---
Outline:
(01:24) Danger, Will Robinson
(02:34) Progress Fast and Slow
(05:02) Statements of Support For Pacing the Frontier
(14:00) No One In Charge
(14:56) Pacing The Frontier
(15:46) Pausing the Frontier
(18:16) Senator Sanders Demands A Pause
(22:00) Moderate Prudence
(25:14) That Escalated Quickly
(26:17) If You Are In Mundane Alignment Pivot To Scalable Alignment
(30:47) Taking It Fast
(31:44) Full Speed Ahead
(32:57) Suicide Squad
(34:19) Prepare To Adjust Your Pace

---

First published:
August 10th, 2026

Source:
https://www.lesswrong.com/posts/WgWoJPKw5b2XTDD24/the-pacing-of-the-frontier

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Bar graph showing — “The Pacing of the Frontier” by Zvi Aug 10, 2026
Show notes

In the wake of the letter calling on us to prepare to potentially Pace the Frontier, there has been much discussion of when pacing the frontier would be prudent, and whether it makes sense to prepare to do so.

This has now been informed by the events surrounding OpenAI training models for months while they had access to a joint de facto message board, which was detected only in the wake of the hacking of HuggingFace by OpenAI's AIs models during a cybersecurity eval. As we find out more about that, a lot of people have grown far more alarmed, as they should given what they previously believed about the difficulty of alignment, about the state of capabilities and about the level of operational supervision, infrastructure, safety and safety culture at the frontier labs.

This post will not go further into the details of that incident. It treats that as background to keep in mind, and mostly involves perspectives from before the Black Hat talk. This was originally scheduled for Friday and got bumped.

A lot of the disagreements about the need to pace tie into expectations about the default pace of capability advancements. As I [...]

---
Outline:
(01:24) Danger, Will Robinson
(02:34) Progress Fast and Slow
(05:02) Statements of Support For Pacing the Frontier
(14:00) No One In Charge
(14:56) Pacing The Frontier
(15:46) Pausing the Frontier
(18:16) Senator Sanders Demands A Pause
(22:00) Moderate Prudence
(25:14) That Escalated Quickly
(26:17) If You Are In Mundane Alignment Pivot To Scalable Alignment
(30:47) Taking It Fast
(31:44) Full Speed Ahead
(32:57) Suicide Squad
(34:19) Prepare To Adjust Your Pace

---

First published:
August 10th, 2026

Source:
https://www.lesswrong.com/posts/WgWoJPKw5b2XTDD24/the-pacing-of-the-frontier

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Person in Joker costume at — “What Happened: OpenAI and HuggingFace” by Zvi Aug 08, 2026
Show notes

Today I am taking the time to write the shorter, simpler version of What Happened.

For those who want all the details, to see my sources, and to see how the story was uncovered and put together, I recommend watching the Black Hat presentation, and I have a series of long posts.

In order:

OpenAI Shares Some Alignment Problems

OpenAI Model Hacks Into HuggingFace During Cybersecurity Evaluation

More on An Internal OpenAI Model Hacking Into HuggingFace

Further Developments About Internal AI Models Hacking Things

OpenAI Trained Its Models For Months While Those Models Were Coordinating Exploits Via Message Boards

This post instead walks through the events themselves, as they happened, as my version of the Black Hat presentation.

There are three versions: Even Shorter, Shorter and Merely Short.

Table of Contents

The Even Shorter Version.

The Shorter Version.

Phase 1: OpenAI Models Training On Impossible Tasks Try Hacking.

Phase 1: The Four Failures.

Phase 2: The Message Board.

Phase 2: The Total Failure.

Phase 3: We Get Lucky And Galaxy Mainly Hacked OpenAI and HuggingFace.

Phase 3: The [...]

---
Outline:
(01:15) The Even Shorter Version
(02:34) The Shorter Version
(04:45) Phase 1: OpenAI Models Training On Impossible Tasks Try Hacking
(05:50) Phase 1: The Four Failures
(07:37) Phase 2: The Message Board
(09:40) Phase 2: The Total Failure
(12:24) Phase 3: We Get Lucky And Galaxy Mainly Hacked OpenAI and HuggingFace
(14:31) Phase 3: The Details
(17:03) Phase 4: The Investigation and Reaction

---

First published:
August 8th, 2026

Source:
https://www.lesswrong.com/posts/xPAxz4g96uKz9FrHs/what-happened-openai-and-huggingface

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

This image is not a tweet.

Person in purple suit and hat drinking coffee amid flames. — “What Happened: OpenAI and HuggingFace” by Zvi Aug 08, 2026
Show notes

Today I am taking the time to write the shorter, simpler version of What Happened.

For those who want all the details, to see my sources, and to see how the story was uncovered and put together, I recommend watching the Black Hat presentation, and I have a series of long posts.

In order:

OpenAI Shares Some Alignment Problems

OpenAI Model Hacks Into HuggingFace During Cybersecurity Evaluation

More on An Internal OpenAI Model Hacking Into HuggingFace

Further Developments About Internal AI Models Hacking Things

OpenAI Trained Its Models For Months While Those Models Were Coordinating Exploits Via Message Boards

This post instead walks through the events themselves, as they happened, as my version of the Black Hat presentation.

There are three versions: Even Shorter, Shorter and Merely Short.

Table of Contents

The Even Shorter Version.

The Shorter Version.

Phase 1: OpenAI Models Training On Impossible Tasks Try Hacking.

Phase 1: The Four Failures.

Phase 2: The Message Board.

Phase 2: The Total Failure.

Phase 3: We Get Lucky And Galaxy Mainly Hacked OpenAI and HuggingFace.

Phase 3: The [...]

---
Outline:
(01:15) The Even Shorter Version
(02:34) The Shorter Version
(04:45) Phase 1: OpenAI Models Training On Impossible Tasks Try Hacking
(05:50) Phase 1: The Four Failures
(07:37) Phase 2: The Message Board
(09:40) Phase 2: The Total Failure
(12:24) Phase 3: We Get Lucky And Galaxy Mainly Hacked OpenAI and HuggingFace
(14:31) Phase 3: The Details
(17:03) Phase 4: The Investigation and Reaction

---

First published:
August 8th, 2026

Source:
https://www.lesswrong.com/posts/xPAxz4g96uKz9FrHs/what-happened-openai-and-huggingface

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Repeated Joker-styled man with gold hat, purple suit. — “OpenAI Trained Its Models For Months While Those Models Were Coordinating Exploits Via Message Boards” by Zvi Aug 07, 2026
Show notes

How does the situation keep turning out to be worse than we know?

How much should we update, therefore, that it is a lot worse than we know, after accounting for all the things we now know?

At some point, when the ‘oh this was a harmless thing’ defenses for AIs doing misaligned actions get demolished enough times in a row by news a few days later, you want to update in advance that usually the reports are not referring to the harmless ordinary versions of things.

Either way, buckle up for the next set of revelations. It's a doozy. This was an early recreation of the triggering events of If Anyone Builds It, Everyone Dies, except it was more sci-fi, because real life does not have to do fake things to look realistic. We were fortunate enough, and this was early enough, that we were able to catch this before it was too late. Next time, if we don’t get our act together, we might not be so lucky.

If I am understanding the Black Hat video correctly, every model OpenAI trained, over a period of multiple months, should be presumed to be hopelessly [...]

---
Outline:
(02:39) Cyber Evals Are A Cursed Basin
(05:16) Outside Of Cyber Evals Is Still Sufficiently Cursed
(06:51) Cheat Cheat Cheat Cheat Cheat
(12:07) Read The Message Board
(14:48) Updating Your AI (Exploitation of OpenAI Internal Systems) Timelines
(18:11) This Is The Way The World Ends
(21:45) Shooting The Messenger Board
(27:16) The Internal and HuggingFace Hacks
(30:33) OpenAI Responds
(33:27) When AIs Tell You Who They Are
(35:43) The Once and Future Rise Of Functional Decision Theory
(41:28) Don't Panic
(43:38) Hackery In the UK
(48:02) Mythos Knew It Was Real This Time
(50:09) I Got 141,006 Test Runs With An Unintentional Open Path To The Internet And An Email Alert Aint One
(53:46) Surely By Now You Know These Are Not Publicity Stunts
(55:24) The Future Is Coming
(57:17) The Investigations Begin
(01:00:08) N Boats And Three Helicopters
(01:01:43) Always Be Sandbox Red Teaming
(01:12:54) Halt And Catch Fire
(01:14:31) Truth and Reconciliation

---

First published:
August 7th, 2026

Source:
https://www.lesswrong.com/posts/noXXv7PwwFqauTBFQ/openai-trained-its-models-for-months-while-those-models-were

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Well-dressed man with glasses, text — “OpenAI Trained Its Models For Months While Those Models Were Coordinating Exploits Via Message Boards” by Zvi Aug 07, 2026
Show notes

How does the situation keep turning out to be worse than we know?

How much should we update, therefore, that it is a lot worse than we know, after accounting for all the things we now know?

At some point, when the ‘oh this was a harmless thing’ defenses for AIs doing misaligned actions get demolished enough times in a row by news a few days later, you want to update in advance that usually the reports are not referring to the harmless ordinary versions of things.

Either way, buckle up for the next set of revelations. It's a doozy. This was an early recreation of the triggering events of If Anyone Builds It, Everyone Dies, except it was more sci-fi, because real life does not have to do fake things to look realistic. We were fortunate enough, and this was early enough, that we were able to catch this before it was too late. Next time, if we don’t get our act together, we might not be so lucky.

If I am understanding the Black Hat video correctly, every model OpenAI trained, over a period of multiple months, should be presumed to be hopelessly [...]

---
Outline:
(02:39) Cyber Evals Are A Cursed Basin
(05:16) Outside Of Cyber Evals Is Still Sufficiently Cursed
(06:51) Cheat Cheat Cheat Cheat Cheat
(12:07) Read The Message Board
(14:48) Updating Your AI (Exploitation of OpenAI Internal Systems) Timelines
(18:11) This Is The Way The World Ends
(21:45) Shooting The Messenger Board
(27:16) The Internal and HuggingFace Hacks
(30:33) OpenAI Responds
(33:27) When AIs Tell You Who They Are
(35:43) The Once and Future Rise Of Functional Decision Theory
(41:28) Don't Panic
(43:38) Hackery In the UK
(48:02) Mythos Knew It Was Real This Time
(50:09) I Got 141,006 Test Runs With An Unintentional Open Path To The Internet And An Email Alert Aint One
(53:46) Surely By Now You Know These Are Not Publicity Stunts
(55:24) The Future Is Coming
(57:17) The Investigations Begin
(01:00:08) N Boats And Three Helicopters
(01:01:43) Always Be Sandbox Red Teaming
(01:12:54) Halt And Catch Fire
(01:14:31) Truth and Reconciliation

---

First published:
August 7th, 2026

Source:
https://www.lesswrong.com/posts/noXXv7PwwFqauTBFQ/openai-trained-its-models-for-months-while-those-models-were

---

Narrated by TYPE III AUDIO.

---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Related Podcasts