Reflections from red-teaming Codex auto-review
Apollo red-teamed OpenAI's Codex auto-review, an AI monitor that approves coding-agent actions, finding authorization and delegation vulnerabilities and recommending fixes.
Research
Apollo Research
Understanding and evaluating deceptive AI. apolloresearch.ai
Focus All
Topic Control + Agents
Source Apollo Research · 4
Date Any time
1 item
1 item
Red-teaming auto mode: lessons from our first external monitor campaign with Anthropic
Apollo Research red-teams Anthropic's auto mode, a monitor that blocks risky Claude Code agent actions, using injected failures, static benchmarks and off-policy attacks, and reports lessons.
1 item
Apollo x Tailscale: Introducing “Watcher” for AI Oversight & Control
Apollo Research and Tailscale announce Watcher, a monitoring layer that flags over twenty failure modes in AI coding agents, including deception and dangerous code execution.
1 item
Apollo’s product vision
Apollo Research announces a product vision for safety tools that secure frontier AI agents, starting with monitoring and real-time intervention for coding agents.