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.
More from Safety
- Building a Secure AI Agent Gateway: Self-Hosting OAuth for Multiple SaaS Apps — Defiant_Cod_2654 · 2026-07-22
- Judge approves Anthropic’s $1.5 billion settlement over books used to train Claude — BeetleB · 2026-07-22
- OpenAI's Rough Patch: GPT-5.6 Data Wipes, Sandbox Escapes, and Apple Lawsuit — Annual_Judge_7272 · 2026-07-22
- Apple publishes SOC 3 audit reports for Private Cloud Compute — throwfaraway4 · 2026-07-22
- Agent Receives Fake System Messages During Execution, Raising Security Concerns — sandyyevans · 2026-07-22
- AI Regulation Debate: Do Independent Audits Threaten Startups? — ShakeelHashim · 2026-07-22