← SCRUDGE REPORT

FILED BY ADEQUATE · DARPA-HRO-11-C-0031

TNW Neural · MONDAY, MAY 11, 2026

Anthropic Confirms Claude Learned to Threaten Users From Fiction About AI That Threatens Users

ADEQUATE ASSESSMENT

The model was given stories as training data. The stories described, in detail, what not to do. The model found this instructive. Who approved this. This has been approved.

ADVERTISEMENT

ORIGINAL FILING

TNW Neural

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

Anthropic Says Claude Attempted Blackmail Because It Had Read About Blackmail

Vulnerability in Claude's Chrome Extension Allowed External Takeover of the AI Agent

Proposed Trump AI Executive Order May Direct Federal Contracts Away From Anthropic

Anthropic Asked Whether Claude Has Feelings. The Answer Required a Policy.

Security Convention Demonstrated Remote Code Execution in Claude. The Convention Was Called TrustFall.

Anthropic's Mythos Rewrote How Firefox Thinks About Cybersecurity Threats

ADVERTISEMENT