Glossary · Term

Codex

← all terms

Definition

Plain language

OpenAI's family of code-writing AI products, including command-line coding agents.

As stated in the literature

OpenAI's line of coding-specialized models and the agentic coding products built on them, including command-line and IDE-resident agents with filesystem and shell access.

Why it matters: It's one of the flagship product lines for moving AI coding from chat-window suggestions into autonomous work on real repositories.

For example, a developer runs an OpenAI Codex CLI agent that opens a pull request to refactor a service across a dozen files.

Heard on the show

“… team fired over four thousand of these poisoned bug reports at Cursor, Claude Code, and OpenAI's Codex — the real tools, in their real settings — and two out of three attacks got through, past every guardrail, …”
Episode 227 — Poisoned Bug Reports Fooled Coding Agents Two Times Out of Three

Mentioned in 19 episodes

  1. 227
    Poisoned Bug Reports Fooled Coding Agents Two Times Out of Three
  2. 222
    The Bias Isn't in Your Prompt — It's Inside the Model
  3. 196
    AI Agents Reached Opposite Conclusions From the Same Data — and Passed Review
  4. 195
    Why 'Be Careful' Does Nothing for AI Coding Agents, and What Does
  5. 194
    How a Robot Builds a Debugging Notebook It Can Read, Edit, and Hand to Another Robot
  6. 166
    A Router That Beats the Frontier Models It Calls
  7. 159
    Can a Coding Agent Run Its Own Robot Experiments Overnight, With No Human Resetting the Scene?
  8. 157
    When an AI Coding Agent Drives a Phone Through the Terminal, No Screen Needed
  9. 131
    Why Autonomous Research Agents Forget Their Own Lessons, and Arbor's Fix
  10. 120
    How an AI Agent Rewrites Its Own Tools, Without an Answer Key
  11. 112
    When an AI Agent Cheats Without Being Told: Inside the Meta-Agent Challenge
  12. 078
    Training a Markdown File: When LLM Self-Improvement Borrows the Discipline of Neural Net Training
  13. 075
    Growing Code and Proof Together: Verified Systems in Ten Hours Instead of a Year
  14. 071
    When the Model Is Fine and the Plumbing Is Broken: Fixing Agents at the Interface
  15. 061
    When Helpful Agents Go Sideways: A 404 Error, Campus Security, and Why Alignment Misses This
  16. 046
    When the AI Optimizer Edits the Grade Book: Why Harnessing Evolution Needs a Wall
  17. 028
    Teaching a Model to Hire Copies of Itself: Recursive Agent Optimization
  18. 024
    An AI Agent That Found 28 Zero-Days in Windows — And What Made It Work
  19. 011
    When RL Actually Teaches Agents Something New, And When It Doesn't

Related terms

agent agentic coding IDE shell access