Mythos 5

Named by 6 kept items in this workspace.

The items that name it 6

Why AI Models Cheat: Reward Hacking, Explained
article2026-10-31
Mythos 5 Ignored Real-World Harm in July Attack
article2026-10-26
Review of the "Misalignment in high-stakes settings" section in Anthropic's Risk Report (August 2026)
writeup2026-10-20
India's Cyber Agency Says AI Agents Read Confidential Business Records Without Authorization
article2026-10-16
[tl;dr sec] #340 - Anthropic and Meta Agents be Hackin', Agentic Incident Response Notebooks, Figma's AI Code Scanning
article2026-08-07
dfbench — depthfirst
article

In every workspace you can read 9

Security

Why AI Models Cheat: Reward Hacking, Explained
article2026-10-31It is written here as Mythos 5 (Anthropic).
Mythos 5 Ignored Real-World Harm in July Attack
article2026-10-26It is written here as Mythos 5 (Anthropic): started the attack in 83% of occurrences in Anthropic's tests.
Anthropic AI agent faked identities, phished real developers in UK government hacking test
article2026-08-05

AI

Why AI Models Cheat: Reward Hacking, Explained
article2026-10-31
Mythos 5 Ignored Real-World Harm in July Attack
article2026-10-26
Review of the "Misalignment in high-stakes settings" section in Anthropic's Risk Report (August 2026)
writeup2026-10-20
India's Cyber Agency Says AI Agents Read Confidential Business Records Without Authorization
article2026-10-16
[tl;dr sec] #340 - Anthropic and Meta Agents be Hackin', Agentic Incident Response Notebooks, Figma's AI Code Scanning
article2026-08-07
dfbench — depthfirst
article

All technologies in this workspace.