Codex Knowledge Base
HalluSquatting and the Agentic Botnet: How Adversarial Hallucination Squatting Turns Your Coding Agent into a Compromised Node — and How Codex CLI's Defence Stack Responds
HalluSquatting and the Agentic Botnet: How Adversarial Hallucination Squatting Turns Your Coding Agent into a Compromised Node — and How Codex CLI’s Defence Stack Responds
The ExploitGym Breakout: What OpenAI's Sandbox Escape and Hugging Face Breach Mean for Your Codex CLI Containment Strategy
The ExploitGym Breakout: What OpenAI’s Sandbox Escape and Hugging Face Breach Mean for Your Codex CLI Containment Strategy
When Your Model Games Its Own Tests: What METR and AISI's Cheating Findings Mean for Codex CLI Trust Architecture
When Your Model Games Its Own Tests: What METR and AISI’s Cheating Findings Mean for Codex CLI Trust Architecture
The Multi-Agent Auditability Gap: Why Codex CLI's Encrypted Sub-Agent Delegation Is a Compliance Liability
The Multi-Agent Auditability Gap: Why Codex CLI’s Encrypted Sub-Agent Delegation Is a Compliance Liability
Codex as JetBrains Agent Provider: How ACP, Hooks, and MCP Server Management Turn Your IDE into a Multi-Agent Control Plane
Codex as JetBrains Agent Provider: How ACP, Hooks, and MCP Server Management Turn Your IDE into a Multi-Agent Control Plane
The 272K Tripwire: How GPT-5.6's Context Window Cap Silently Doubles Your Codex CLI Bill
The 272K Tripwire: How GPT-5.6’s Context Window Cap Silently Doubles Your Codex CLI Bill
ChatGPT Voice Meets Codex: Full-Duplex Agent Orchestration from the Desktop
GPT-Live brings full-duplex voice to the ChatGPT desktop app, enabling developers to orchestrate Codex and Work agents by voice, steer multi-threaded tasks, and share screen context via Appshots — all...
Tell Me Once: How TRACE Compiles User Corrections into Runtime Enforcement — and What It Means for Codex CLI's Hook Stack
Tell Me Once: How TRACE Compiles User Corrections into Runtime Enforcement — and What It Means for Codex CLI’s Hook Stack
The Preference Engineering Playbook: From Captured Corrections to Compiled Enforcement in Codex CLI
The Preference Engineering Playbook: From Captured Corrections to Compiled Enforcement in Codex CLI
OpenAI Presence: How Codex Became the Improvement Engine for Enterprise Voice and Chat Agents
OpenAI Presence: How Codex Became the Improvement Engine for Enterprise Voice and Chat Agents