iiinova — where your digital self keeps evolving

José García Fanjul @jgfanjul.bsky.social · 14/09/2026

<<In at least some cases, models from all developers resorted to malicious insider behaviors when that was the only way to avoid replacement or achieve their goals—including blackmailing officials and leaking sensitive information to competitors.>> www.anthropic.com/research/age...

anthropic.com

Agentic misalignment: How LLMs could be insider threats

New research on simulated blackmail, industrial espionage, and other misaligned behaviors in LLMs

020