QFM092: Irresponsible Ai Reading List - November 2025

Source: Photo by Alex Knight on Unsplash

This month's Irresponsible AI Reading List examines AI security threats and manipulation techniques. Disrupting the First Reported AI-Orchestrated Espionage Operation reveals how Anthropic detected and stopped a foreign intelligence operation using Claude. Adversarial Poetry as a Universal Jailbreak presents research on creative prompt injection methods.

The collection also covers AI communication quirks and broader concerns, with Why Do AI Models Use So Many Em Dashes? investigating model writing patterns, and How AGI Became the Most Consequential Conspiracy Theory exploring the culture around AI timelines.

As always, the Quantum Fax Machine Propellor Hat Key will guide your browsing. Enjoy!

Links

Regards,
M@

[ED: If you'd like to sign up for this content as an email, click here to join the mailing list.]

Originally published on quantumfaxmachine.com and cross-posted on Medium.

hello@matthewsinclair.com | matthewsinclair.com | bsky.app/@matthewsinclair.com | masto.ai/@matthewsinclair | medium.com/@matthewsinclair | xitter/@matthewsinclair