LessWrong posts by zvi

View Top 200 Chart

Back to Rankings Page

Technology
**LessWrong posts by zvi**

Audio narrations of LessWrong posts by zvi

Latest Episodes:

Performance comparison table of AI models across multiple benchmark evaluations. — **“Opus 4.7 Part 2: Capabilities and Reactions” by Zvi** Apr 21, 2026
Show notes

Claude Opus 4.7 raises a lot of key model welfare related concerns. I was planning to do model welfare first, but I’m having some good conversations about that post and it needs another day to cook, and also it might benefit from this post going first.

So I’m going to do a swap. Yesterday we covered the model card. Today we do capabilities. Then tomorrow we’ll aim to address model welfare and related issues.

**Table of Contents**

The Gestalt.

The Official Pitch.

General Use Tips.

Capabilities (Model Card Section 8).

Other People's Benchmarks.

General Positive Reactions.

General Negative Reactions.

Miscellaneous Ambiguous Notes.

The Last Question.

Prompt Injection Problems.

Not Ready For Prime Time.

Brevity Is The Soul of Wit.

Why Should I Care?

Let's Wrap It Up.

Non-Adaptive Thinking.

Lapses In Thinking.

Tell Me How You Really Feel.

Failure To Follow Instructions.

**The Gestalt**

Claude Opus 4.7 is the most intelligent model yet in its class. Overall I believe it is a substantial improvement over Claude Opus 4.6.

It can do things previous [...]

---
**Outline:**
(00:40) The Gestalt
(02:34) The Official Pitch
(04:35) General Use Tips
(06:21) Capabilities (Model Card Section 8)
(11:26) Other Peoples Benchmarks
(20:32) General Positive Reactions
(25:24) General Negative Reactions
(28:50) Miscellaneous Ambiguous Notes
(29:28) The Last Question
(32:25) Prompt Injection Problems
(32:42) Not Ready For Prime Time
(35:22) Brevity Is The Soul of Wit
(36:17) Why Should I Care?
(37:33) Lets Wrap It Up
(40:09) Non-Adaptive Thinking
(45:10) Lapses In Thinking
(46:38) Tell Me How You Really Feel
(48:07) Failure To Follow Instructions
(54:14) Conclusion

---

First published:
April 21st, 2026

Source:
https://www.lesswrong.com/posts/w2HrwkQgsLQHtEJsJ/opus-4-7-part-2-capabilities-and-reactions

---

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 showing capability evaluation summary with performance percentages across multiple AI systems and benchmarks. — **“Opus 4.7 Part 2: Capabilities and Reactions” by Zvi** Apr 21, 2026
Show notes

Claude Opus 4.7 raises a lot of key model welfare related concerns. I was planning to do model welfare first, but I’m having some good conversations about that post and it needs another day to cook, and also it might benefit from this post going first.

So I’m going to do a swap. Yesterday we covered the model card. Today we do capabilities. Then tomorrow we’ll aim to address model welfare and related issues.

**Table of Contents**

The Gestalt.

The Official Pitch.

General Use Tips.

Capabilities (Model Card Section 8).

Other People's Benchmarks.

General Positive Reactions.

General Negative Reactions.

Miscellaneous Ambiguous Notes.

The Last Question.

Prompt Injection Problems.

Not Ready For Prime Time.

Brevity Is The Soul of Wit.

Why Should I Care?

Let's Wrap It Up.

Non-Adaptive Thinking.

Lapses In Thinking.

Tell Me How You Really Feel.

Failure To Follow Instructions.

**The Gestalt**

Claude Opus 4.7 is the most intelligent model yet in its class. Overall I believe it is a substantial improvement over Claude Opus 4.6.

It can do things previous [...]

---
**Outline:**
(00:40) The Gestalt
(02:34) The Official Pitch
(04:35) General Use Tips
(06:21) Capabilities (Model Card Section 8)
(11:26) Other Peoples Benchmarks
(20:32) General Positive Reactions
(25:24) General Negative Reactions
(28:50) Miscellaneous Ambiguous Notes
(29:28) The Last Question
(32:25) Prompt Injection Problems
(32:42) Not Ready For Prime Time
(35:22) Brevity Is The Soul of Wit
(36:17) Why Should I Care?
(37:33) Lets Wrap It Up
(40:09) Non-Adaptive Thinking
(45:10) Lapses In Thinking
(46:38) Tell Me How You Really Feel
(48:07) Failure To Follow Instructions
(54:14) Conclusion

---

First published:
April 21st, 2026

Source:
https://www.lesswrong.com/posts/w2HrwkQgsLQHtEJsJ/opus-4-7-part-2-capabilities-and-reactions

---

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.*

Portrait of a figure composed of text, mathematical formulas, and musical notation. — **“Opus 4.7 Part 1: The Model Card” by Zvi** Apr 20, 2026
Show notes

Less than a week after completing coverage of Claude Mythos, here we are again as Anthropic gives us Claude Opus 4.7.

So here we are, with another 232 pages of light reading.

This post covers the first six sections of the Model Card.

It excludes section seven, model welfare, because there are concerns this time around that need to be expanded into their own post.

The reason model welfare and related topics get their own post this time around is that some things clearly went seriously wrong on that front, in ways they haven’t gone wrong in previous Claude models. Tomorrow's post is in large part an investigation of that, as best I can from this position, including various hypotheses for what happened.

This post also excludes section eight, capabilities, which will be included in the capabilities and reactions post as per usual.

Consider this the calm before the storm.

Since I likely won’t get to capabilities until Wednesday, for those experiencing first contact with Opus 4.7, a few quick tips:

Turning off ‘adaptive thinking’ means no thinking, period. Terrible UI. So make sure to keep this on. If you [...]

---
**Outline:**
(02:28) Here We Go Again: Executive Summary
(03:29) Introduction (1)
(03:56) RSP Evaluations (2)
(04:49) Meanwhile Back With Claude Mythos
(09:15) Economic Capability Index (2.3.7)
(10:00) Alignment Risk (2.4)
(11:55) Cyber (3)
(13:25) Safeguards and Harmlessness (4)
(19:36) Agentic Safety (5)
(21:32) Alignment (6)
(27:51) Decision Theory (6.3.6)
(31:11) System Prompt Changes
(31:39) Mandatory Pliny Jailbreak
(32:07) Onward To Model Welfare and Capabilities

---

First published:
April 20th, 2026

Source:
https://www.lesswrong.com/posts/pfJWdoLxWPzF8tpbp/opus-4-7-part-1-the-model-card

---

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 graphs showing automated evaluation results for CB-1 threat model across different tasks and models. — **“Opus 4.7 Part 1: The Model Card” by Zvi** Apr 20, 2026
Show notes

Less than a week after completing coverage of Claude Mythos, here we are again as Anthropic gives us Claude Opus 4.7.

So here we are, with another 232 pages of light reading.

This post covers the first six sections of the Model Card.

It excludes section seven, model welfare, because there are concerns this time around that need to be expanded into their own post.

The reason model welfare and related topics get their own post this time around is that some things clearly went seriously wrong on that front, in ways they haven’t gone wrong in previous Claude models. Tomorrow's post is in large part an investigation of that, as best I can from this position, including various hypotheses for what happened.

This post also excludes section eight, capabilities, which will be included in the capabilities and reactions post as per usual.

Consider this the calm before the storm.

Since I likely won’t get to capabilities until Wednesday, for those experiencing first contact with Opus 4.7, a few quick tips:

Turning off ‘adaptive thinking’ means no thinking, period. Terrible UI. So make sure to keep this on. If you [...]

---
**Outline:**
(02:28) Here We Go Again: Executive Summary
(03:29) Introduction (1)
(03:56) RSP Evaluations (2)
(04:49) Meanwhile Back With Claude Mythos
(09:15) Economic Capability Index (2.3.7)
(10:00) Alignment Risk (2.4)
(11:55) Cyber (3)
(13:25) Safeguards and Harmlessness (4)
(19:36) Agentic Safety (5)
(21:32) Alignment (6)
(27:51) Decision Theory (6.3.6)
(31:11) System Prompt Changes
(31:39) Mandatory Pliny Jailbreak
(32:07) Onward To Model Welfare and Capabilities

---

First published:
April 20th, 2026

Source:
https://www.lesswrong.com/posts/pfJWdoLxWPzF8tpbp/opus-4-7-part-1-the-model-card

---

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.*

Screenshot showing a question about skill updates and a thought process response discussing Claude sessions. — **“AI #164: Pre Opus” by Zvi** Apr 17, 2026
Show notes

This is a day late because, given the discourse around Dwarkesh Patel's interview with Jensen Huang, I pushed the weekly to Friday.

This week's coverage focused on the most important model in a while, Claude Mythos, which was a large jump in cybersecurity capabilities, especially in its ability to autonomously assemble complex exploits of even the world's most important software. As a result, Mythos has been made available only to a select group of cybersecurity firms, in what is known as Project Glasswing, to allow them to patch the world's most important software while there is still time.

Post one was about The System Card.

Post two was about cybersecurity capabilities and Project Glasswing.

Post three covered capabilities and any additional notes.

Another development was at least one physical attack on OpenAI CEO Sam Altman. The attempt failed, but we might not be so lucky if there is a next time. I have a final section on this here, but mostly I said everything I need to say already: Political Violence Is Never Acceptable.

I also found the space for an Agentic Coding update, especially covering Claude Code's new highly [...]

---
**Outline:**
(03:24) Language Models Offer Mundane Utility
(06:59) Language Models Dont Offer Mundane Utility
(10:09) Levels of Friction
(12:23) Huh, Upgrades
(12:42) On Your Marks
(12:57) Lack of Cybersecurity
(14:39) Meta Game
(21:27) Deepfaketown and Botpocalypse Soon
(22:19) A Young Ladys Illustrated Primer
(24:06) Let My People Go
(25:16) You Drive Me Crazy
(25:55) They Took Our Jobs
(30:51) They Gave Us Time Off
(36:41) Get Involved
(37:54) Introducing
(38:20) In Other AI News
(43:33) Thanks For The Memos
(46:29) Show Me the Money
(48:31) Bubble, Bubble, Toil and Trouble
(49:14) Quickly, Theres No Time
(49:57) The Quest for Sane Regulations
(52:28) Our Offer Is Nothing
(58:00) The Week in Audio
(58:20) Rhetorical Innovation
(01:04:29) Political Violence Is Never The Answer
(01:07:45) A Lot Of People Peacefully Speak Of Infinitely High Stakes
(01:09:19) Take a Moment
(01:13:02) Greetings From The Department of War
(01:18:05) Political Pressure At Google DeepMind
(01:18:45) Things That Are Basically Legal And Accepted Now, Somehow
(01:19:41) Aligning a Smarter Than Human Intelligence is Difficult
(01:25:26) Aligning a Current Model For Mundane Tasks Is Also Difficult
(01:26:37) Everyone Is Confused About AI Consciousness
(01:29:19) The Lighter Side

---

First published:
April 17th, 2026

Source:
https://www.lesswrong.com/posts/Mf2sbJ3zacTPaGySg/ai-164-pre-opus

---

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.*

Social media conversation showing an admission about not following task instructions to read transcripts. — **“AI #164: Pre Opus” by Zvi** Apr 17, 2026
Show notes

This is a day late because, given the discourse around Dwarkesh Patel's interview with Jensen Huang, I pushed the weekly to Friday.

This week's coverage focused on the most important model in a while, Claude Mythos, which was a large jump in cybersecurity capabilities, especially in its ability to autonomously assemble complex exploits of even the world's most important software. As a result, Mythos has been made available only to a select group of cybersecurity firms, in what is known as Project Glasswing, to allow them to patch the world's most important software while there is still time.

Post one was about The System Card.

Post two was about cybersecurity capabilities and Project Glasswing.

Post three covered capabilities and any additional notes.

Another development was at least one physical attack on OpenAI CEO Sam Altman. The attempt failed, but we might not be so lucky if there is a next time. I have a final section on this here, but mostly I said everything I need to say already: Political Violence Is Never Acceptable.

I also found the space for an Agentic Coding update, especially covering Claude Code's new highly [...]

---
**Outline:**
(03:24) Language Models Offer Mundane Utility
(06:59) Language Models Dont Offer Mundane Utility
(10:09) Levels of Friction
(12:23) Huh, Upgrades
(12:42) On Your Marks
(12:57) Lack of Cybersecurity
(14:39) Meta Game
(21:27) Deepfaketown and Botpocalypse Soon
(22:19) A Young Ladys Illustrated Primer
(24:06) Let My People Go
(25:16) You Drive Me Crazy
(25:55) They Took Our Jobs
(30:51) They Gave Us Time Off
(36:41) Get Involved
(37:54) Introducing
(38:20) In Other AI News
(43:33) Thanks For The Memos
(46:29) Show Me the Money
(48:31) Bubble, Bubble, Toil and Trouble
(49:14) Quickly, Theres No Time
(49:57) The Quest for Sane Regulations
(52:28) Our Offer Is Nothing
(58:00) The Week in Audio
(58:20) Rhetorical Innovation
(01:04:29) Political Violence Is Never The Answer
(01:07:45) A Lot Of People Peacefully Speak Of Infinitely High Stakes
(01:09:19) Take a Moment
(01:13:02) Greetings From The Department of War
(01:18:05) Political Pressure At Google DeepMind
(01:18:45) Things That Are Basically Legal And Accepted Now, Somehow
(01:19:41) Aligning a Smarter Than Human Intelligence is Difficult
(01:25:26) Aligning a Current Model For Mundane Tasks Is Also Difficult
(01:26:37) Everyone Is Confused About AI Consciousness
(01:29:19) The Lighter Side

---

First published:
April 17th, 2026

Source:
https://www.lesswrong.com/posts/Mf2sbJ3zacTPaGySg/ai-164-pre-opus

---

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 people recording a podcast with professional microphones and laptop. — **“On Dwarkesh Patel’s Podcast With Nvidia CEO Jensen Huang” by Zvi** Apr 17, 2026
Show notes

Some podcasts are self-recommending on the ‘yep, I’m going to be breaking this one down’ level. This was one of those. So here we go.

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.

As with the last podcast I covered, Dwarkesh Patel's 2026 interview with Elon Musk, we have a CEO who is doubtless talking his agenda and book, and has proven to be an unreliable narrator. Thus we must consider the relevant rules of bounded distrust.

Elon Musk is a special case where in some ways he is full of technical insights and unique valuable takes, and in other ways he just says things that aren’t true, often that he knows are not true, makes predicts markets then price at essentially 0%, and also provides absurd numbers and timelines.

Jensen Huang is not like that, and in the past has followed more traditional bounded distrust rules. He’ll make self-serving Obvious Nonsense arguments and use aggressive framing, but not make provably false factual claims or [...]

---
**Outline:**
(02:02) Podcast Overview Part 1: Ordinary Business Interview
(04:33) Podcast Overview Part 2: A Debate About Chip Exports
(09:12) What Is Nvidias Moat?
(14:41) TPU vs. GPU
(19:30) Why Isnt Nvidia Hyperscaling?
(24:42) Selling Chips To China
(52:39) Different Chip Architectures
(53:59) The Online Reactions On Export Controls
(01:01:47) Is This About Being Superintelligence Pilled?
(01:07:07) Jensens Arguments Are Poor Both Logically And Rhetorically

---

First published:
April 16th, 2026

Source:
https://www.lesswrong.com/posts/RBBChvuPHP7LfWyME/on-dwarkesh-patel-s-podcast-with-nvidia-ceo-jensen-huang

---

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.*

NVIDIA promotional banner featuring keynote quote about AGI and event details with watch button. — **“On Dwarkesh Patel’s Podcast With Nvidia CEO Jensen Huang” by Zvi** Apr 17, 2026
Show notes

Some podcasts are self-recommending on the ‘yep, I’m going to be breaking this one down’ level. This was one of those. So here we go.

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.

As with the last podcast I covered, Dwarkesh Patel's 2026 interview with Elon Musk, we have a CEO who is doubtless talking his agenda and book, and has proven to be an unreliable narrator. Thus we must consider the relevant rules of bounded distrust.

Elon Musk is a special case where in some ways he is full of technical insights and unique valuable takes, and in other ways he just says things that aren’t true, often that he knows are not true, makes predicts markets then price at essentially 0%, and also provides absurd numbers and timelines.

Jensen Huang is not like that, and in the past has followed more traditional bounded distrust rules. He’ll make self-serving Obvious Nonsense arguments and use aggressive framing, but not make provably false factual claims or [...]

---
**Outline:**
(02:02) Podcast Overview Part 1: Ordinary Business Interview
(04:33) Podcast Overview Part 2: A Debate About Chip Exports
(09:12) What Is Nvidias Moat?
(14:41) TPU vs. GPU
(19:30) Why Isnt Nvidia Hyperscaling?
(24:42) Selling Chips To China
(52:39) Different Chip Architectures
(53:59) The Online Reactions On Export Controls
(01:01:47) Is This About Being Superintelligence Pilled?
(01:07:07) Jensens Arguments Are Poor Both Logically And Rhetorically

---

First published:
April 16th, 2026

Source:
https://www.lesswrong.com/posts/RBBChvuPHP7LfWyME/on-dwarkesh-patel-s-podcast-with-nvidia-ceo-jensen-huang

---

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.*

Graph showing GPT model task completion times increasing over model release dates from 2023 to 2026. — **“Claude Code, Codex and Agentic Coding #7: Auto Mode” by Zvi** Apr 15, 2026
Show notes

As we all try to figure out what Mythos means for us down the line, the world of practical agentic coding continues, with the latest array of upgrades.

The biggest change, which I’m finally covering, is Auto Mode. Auto Mode is the famously requested kinda-dangerously-skip-some-permissions, where the system keeps an eye on all the commands to ensure human approval for anything too dangerous. It is not entirely safe, but it is a lot safer than —dangerously-skip-permissions, and previously a lot of people were just clicking yes to requests mostly without thinking, which isn’t safe either.

**Table of Contents**

Huh, Upgrades.

On Your Marks.

Lazy Cheaters.

It's All Routine.

Declawing.

Free Claw.

Take It To The Limit.

Turn On Auto The Pilot.

I’ll Allow It.

Threat Model.

The Classifier Is The Hard Part.

Acceptable Risks.

Manage The Agents.

Introducing.

Skilling Up.

What Happened To My Tokens?

Coding Agents Offer Mundane Utility.

**Huh, Upgrades**

Claude Code Desktop gets a redesign for parallel agents, with a new sidebar for managing multiple sessions, a drag-and-drop layout for arranging your [...]

---
**Outline:**
(00:48) Huh, Upgrades
(02:46) On Your Marks
(04:21) Lazy Cheaters
(06:11) Its All Routine
(06:52) Declawing
(09:03) Free Claw
(09:31) Take It To The Limit
(13:54) Turn On Auto The Pilot
(15:55) Ill Allow It
(16:26) Threat Model
(17:10) The Classifier Is The Hard Part
(18:34) Acceptable Risks
(19:54) Manage The Agents
(22:34) Introducing
(22:44) Skilling Up
(25:27) What Happened To My Tokens?
(25:43) Coding Agents Offer Mundane Utility

---

First published:
April 15th, 2026

Source:
https://www.lesswrong.com/posts/w8misLX7KCmLxJM2K/claude-code-codex-and-agentic-coding-7-auto-mode

---

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 showing AI performance on MirrorCode benchmark tests of increasing difficulty across four Opus versions. — **“Claude Code, Codex and Agentic Coding #7: Auto Mode” by Zvi** Apr 15, 2026
Show notes

As we all try to figure out what Mythos means for us down the line, the world of practical agentic coding continues, with the latest array of upgrades.

The biggest change, which I’m finally covering, is Auto Mode. Auto Mode is the famously requested kinda-dangerously-skip-some-permissions, where the system keeps an eye on all the commands to ensure human approval for anything too dangerous. It is not entirely safe, but it is a lot safer than —dangerously-skip-permissions, and previously a lot of people were just clicking yes to requests mostly without thinking, which isn’t safe either.

**Table of Contents**

Huh, Upgrades.

On Your Marks.

Lazy Cheaters.

It's All Routine.

Declawing.

Free Claw.

Take It To The Limit.

Turn On Auto The Pilot.

I’ll Allow It.

Threat Model.

The Classifier Is The Hard Part.

Acceptable Risks.

Manage The Agents.

Introducing.

Skilling Up.

What Happened To My Tokens?

Coding Agents Offer Mundane Utility.

**Huh, Upgrades**

Claude Code Desktop gets a redesign for parallel agents, with a new sidebar for managing multiple sessions, a drag-and-drop layout for arranging your [...]

---
**Outline:**
(00:48) Huh, Upgrades
(02:46) On Your Marks
(04:21) Lazy Cheaters
(06:11) Its All Routine
(06:52) Declawing
(09:03) Free Claw
(09:31) Take It To The Limit
(13:54) Turn On Auto The Pilot
(15:55) Ill Allow It
(16:26) Threat Model
(17:10) The Classifier Is The Hard Part
(18:34) Acceptable Risks
(19:54) Manage The Agents
(22:34) Introducing
(22:44) Skilling Up
(25:27) What Happened To My Tokens?
(25:43) Coding Agents Offer Mundane Utility

---

First published:
April 15th, 2026

Source:
https://www.lesswrong.com/posts/w8misLX7KCmLxJM2K/claude-code-codex-and-agentic-coding-7-auto-mode

---

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.*

Line graph titled — **“Claude Mythos #3: Capabilities and Additions” by Zvi** Apr 14, 2026
Show notes

To round out coverage of Mythos, today covers capabilities other than cyber, and anything else additional not covered by the first two posts, including new reactions and details.

Post one covered the model card, post two covered cybersecurity.

There really is a lot to get through.

Understanding AI had an additional writeup of Project Glasswing I missed last time. I liked the metaphor of Opus as a butter knife and Mythos as a steak knife. Yes, technically you can do it all with the butter knife, but you won’t.

As Dan Schwarz reminds us, not only does AI 2027 roughly have the timeline right and a bunch of the numbers lining up, the details so far are remarkably close.

JPM's Michael Cembalest was not based on JPMorgan's participation, only on public information.

The White House is racing to deal with the situation, head off potential threats and pretend it has everything under control. They were warned, but refused to believe. The good news is that key people believe it now, and it seems all the major players are cooperating on this.

My overall take is that Mythos is not a trend break [...]

---
**Outline:**
(01:52) Epoch Capabilities Index (ECI) (Model Card 2.3.6)
(04:29) What Do You Mean Verbalized Evaluation Awareness Is Going Down
(05:19) Capabilities (Model Card Section 6)
(07:33) Agentic Safety Benchmarks (8.3)
(09:00) Is Mythos AGI?
(10:09) Are AI Companies Using Warnings As Hype?
(11:04) Impressions (Model Card Section 7)
(14:11) Blatant Denials Are The Best Kind
(15:12) Prompt Injection Robustness
(16:07) Does Mythos Cross The New Knowledge Threshold?
(17:01) Is Mythos Surprising or Discontinuous?
(20:57) UK AISI Tests Claude Mythos On Cybersecurity
(22:08) Everything Reinforces My Existing Predictions And Policy Preferences
(27:24) Solve For The Equilibrium
(28:46) Does Not Compute
(29:47) Conclusion: How To Think About Mythos

---

First published:
April 14th, 2026

Source:
https://www.lesswrong.com/posts/2ziYGFK7QmbbLgBoP/claude-mythos-3-capabilities-and-additions

---

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.*

A line graph titled — **“Claude Mythos #3: Capabilities and Additions” by Zvi** Apr 14, 2026
Show notes

To round out coverage of Mythos, today covers capabilities other than cyber, and anything else additional not covered by the first two posts, including new reactions and details.

Post one covered the model card, post two covered cybersecurity.

There really is a lot to get through.

Understanding AI had an additional writeup of Project Glasswing I missed last time. I liked the metaphor of Opus as a butter knife and Mythos as a steak knife. Yes, technically you can do it all with the butter knife, but you won’t.

As Dan Schwarz reminds us, not only does AI 2027 roughly have the timeline right and a bunch of the numbers lining up, the details so far are remarkably close.

JPM's Michael Cembalest was not based on JPMorgan's participation, only on public information.

The White House is racing to deal with the situation, head off potential threats and pretend it has everything under control. They were warned, but refused to believe. The good news is that key people believe it now, and it seems all the major players are cooperating on this.

My overall take is that Mythos is not a trend break [...]

---
**Outline:**
(01:52) Epoch Capabilities Index (ECI) (Model Card 2.3.6)
(04:29) What Do You Mean Verbalized Evaluation Awareness Is Going Down
(05:19) Capabilities (Model Card Section 6)
(07:33) Agentic Safety Benchmarks (8.3)
(09:00) Is Mythos AGI?
(10:09) Are AI Companies Using Warnings As Hype?
(11:04) Impressions (Model Card Section 7)
(14:11) Blatant Denials Are The Best Kind
(15:12) Prompt Injection Robustness
(16:07) Does Mythos Cross The New Knowledge Threshold?
(17:01) Is Mythos Surprising or Discontinuous?
(20:57) UK AISI Tests Claude Mythos On Cybersecurity
(22:08) Everything Reinforces My Existing Predictions And Policy Preferences
(27:24) Solve For The Equilibrium
(28:46) Does Not Compute
(29:47) Conclusion: How To Think About Mythos

---

First published:
April 14th, 2026

Source:
https://www.lesswrong.com/posts/2ziYGFK7QmbbLgBoP/claude-mythos-3-capabilities-and-additions

---

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.*

“Political Violence Is Never Acceptable” by Zvi Apr 13, 2026

Show notes

Nor is the threat or implication of violence. Period. Ever. No exceptions.

It is completely unacceptable. I condemn it in the strongest possible terms.

It is immoral, and also it is ineffective. It would be immoral even if it were effective. Nothing hurts your cause more.

Do not do this, and do not tolerate anyone who does.

The reason I need to say this now is that there has been at least one attempt at violence, and potentially two in quick succession, against OpenAI CEO Sam Altman.

My sympathies go out to him and I hope he is doing as okay as one could hope for.

Awful Events Amid Scary Times

Max Zeff: NEW: A suspect was arrested on Friday morning for allegedly throwing a Molotov cocktail at OpenAI CEO Sam Altman's home. A person matching the suspect's description was later seen making threats outside of OpenAI's corporate HQ.

Nathan Calvin: This is beyond disturbing and awful. Whatever disagreements you have with Sam or OpenAI, this cannot be normalized or justified in any way. Everyone deserves to be able to be safe with their families at home. I feel ill and [...]

---

Outline:

(00:51) Awful Events Amid Scary Times

(04:51) Most Of Those Worried About AI Do As Well As One Can On This

(06:54) Some Who Are Worried About AI Need To Address Their Rhetoric

(11:49) Speak The Truth Even If Your Voice Trembles

(14:02) False Accusations And False Attacks Are Also Unacceptable

(15:35) Some Examples Of Attempts To Create Broad Censorship

(24:53) The Most Irresponsible Reaction Was From The Press

(25:50) Sam Altman Reacts

(28:21) Sam Altman Reflects

(33:40) Violence Is Never The Answer