Exploring AI Applications in Offensive Cybersecurity

joshua_saxe · x · 2026-07-10

The author is writing a Substack article on how attackers adopt AI. While using the Opus 4.8 model to analyze vast amounts of threat intelligence, the author shares ethnographic snippets about attacker groups and explores how much practical limitation models with safety guardrails (like Fable or GPT-5.6) can actually impose on these malicious groups.

Original post →

More from Safety

Safety channel →