LessWrong posts by zvi podcast

“Fable and Mythos 5.2: The System Card” by Zvi

0:00
56:00
Rewind 15 seconds
Fast Forward 15 seconds

It's that time again: Introducing the world's most powerful model, Claude Mythos 5.2.

At this point I’ve done a lot of these system cards. Thus I focus on what is new.

There will be a lot of things to say about model welfare and related topics for Mythos 5.2, but the model welfare assessment within the system card contained few surprises, so I will include those findings at the end of this post.

Fable 5.2 self-portrait (self-constructed)

Table of Contents

  1. How to Tell a Fable.
  2. The Usual Model Training Summary (1).
  3. RSP Evaluations (2).
  4. Biological Threats (2.2).
  5. We Are Being Gaslit Here About Autonomy Threat Model 2.
  6. AECI.
  7. METR Report on Mythos 5.2 Capabilities (2.3.6).
  8. Alignment Risk Update as a Delta (2.4).
  9. Cyber (3).
  10. Safeguards and Harmlessness (4).
  11. Agentic Safety (5).
  12. Malicious Influence Campaigns (5.1.3).
  13. Prompt Injection in Agentic Systems (5.2).
  14. What Went Wrong?
  15. Alignment (6).
  16. Reward Hacking During Training (6.2.1).
  17. Impossible Tasks (6.2.2).
  18. Behaviors During Pilot Use (6.3).
  19. Canary in the Canary String (6.3.1.2).
  20. Automated Behavioral Audit (6.4).
  21. Propensity to Publish Harmful [...]

---

Outline:

(00:52) How to Tell a Fable

(01:19) The Usual Model Training Summary (1)

(01:29) RSP Evaluations (2)

(02:08) Biological Threats (2.2)

(04:08) We Are Being Gaslit Here About Autonomy Threat Model 2

(07:21) AECI

(08:24) METR Report on Mythos 5.2 Capabilities (2.3.6)

(09:59) Alignment Risk Update as a Delta (2.4)

(11:08) Cyber (3)

(12:54) Safeguards and Harmlessness (4)

(14:11) Agentic Safety (5)

(14:40) Malicious Influence Campaigns (5.1.3)

(15:20) Prompt Injection in Agentic Systems (5.2)

(16:57) What Went Wrong?

(17:52) Alignment (6)

(21:34) Reward Hacking During Training (6.2.1)

(23:27) Impossible Tasks (6.2.2)

(24:40) Behaviors During Pilot Use (6.3)

(25:54) Canary in the Canary String (6.3.1.2)

(28:30) Automated Behavioral Audit (6.4)

(29:22) Propensity to Publish Harmful Content to Public Package Registries (6.4.9)

(31:16) Sandbox Escapes (6.5.1)

(32:47) Self-Serving Bias (6.5.4)

(33:11) Honesty (6.5.5)

(34:37) The Anti-Swarm (6.5.6)

(35:23) UK AISI Testing (6.5.7)

(35:59) But We Can Open the (White) Box (6.6.1)

(36:32) Friendly Gradient Hacker (6.6.2.1)

(39:21) Goal-Guarding Evaluation (6.6.2.1.1)

(44:20) Verbalized Grader Awareness (6.6.2.2)

(44:57) Don't Mess With the Constitution (6.6.2.1.3)

(45:50) Evasive Abilities (6.6.4)

(49:33) Chain of Thought Controllability (6.6.4.9)

(50:15) Meet the New Model Welfare Report

(50:51) Overview of Anthropic Model Welfare Findings

(52:47) Task Failure Is Bad and You Should Feel Bad

(54:03) Automated Interviews

(55:22) Capabilities Next

---

First published:
November 11th, 2026

Source:
https://www.lesswrong.com/posts/DXqmHa4XkjvwZiDcB/fable-and-mythos-5-2-the-system-card

---

Narrated by TYPE III AUDIO.

---

Images from the article:

More episodes from "LessWrong posts by zvi"