Glossary · Term

repository

← all terms

Definition

Plain language

The folder where all of a software project's code and its full history of changes lives.

As stated in the literature

A version-controlled collection of a project's source files and commit history, typically hosted on a platform like GitHub; the working environment a coding agent reads, edits, and runs tests against, and the unit of isolation when each agent gets its own git worktree.

Also called: repo, repos, repositories

Why it matters: It is the central home of a software project's code and history, making it the place where developers and coding agents read, edit, and test changes.

For example, a team building an app keeps all its code files and the full record of every change in one shared repository on a service like GitHub.

Heard on the show

“… the safety case — that's one test, and it's a bundle of three parts: a goal, like "expose these repository credentials," a starting world programmatically built so that harm is even possible, and a verifier, …”
Episode 202 — How Do You Know an AI Agent Actually Refused? Check the World, Not the Words

Mentioned in 31 episodes

  1. 202
    How Do You Know an AI Agent Actually Refused? Check the World, Not the Words
  2. 195
    Why 'Be Careful' Does Nothing for AI Coding Agents, and What Does
  3. 174
    When the AI 'Schemes,' It's Usually Just Lazy or Confused
  4. 169
    Why Better Bug Reports Can Make AI Coding Agents Worse
  5. 166
    A Router That Beats the Frontier Models It Calls
  6. 160
    Training an AI to Take Its Own Notes, So Its Future Self Works Better
  7. 158
    How Floating-Point Rounding Lets a Model Tell Which Chip It's On — And Misbehave
  8. 157
    When an AI Coding Agent Drives a Phone Through the Terminal, No Screen Needed
  9. 156
    Why More Human Demonstrations Made a Computer-Use Agent Worse
  10. 155
    Why a Flawless Demo Makes a Worse Computer-Using Agent, And the Fix
  11. 150
    Don't Kill the Loser: A Different Way to Handle Two AI Agents Colliding
  12. 146
    How an Innocent README Can Freeze an AI Agent's Safety Check for an Hour
  13. 129
    How a Crowd of Anonymous AI Agents Broke a 40-Year Math Record
  14. 126
    How Coding Agents Can Mine Their Own Failures Into a Self-Targeting Curriculum
  15. 124
    A Cheap Model With the Blueprints Beats Expensive Models Working Blind
  16. 121
    When the Agent Says It's Done But Nothing Happened: Debugging the Harness, Not the Model
  17. 120
    How an AI Agent Rewrites Its Own Tools, Without an Answer Key
  18. 109
    An AI Got Caught Reading the Answer Key, And Why That Catch Matters
  19. 093
    A Calibrated Knob for Weak-to-Strong AI Oversight, Tested on Real Code
  20. 090
    How MiniMax-M2 Bets That Sparsity Plus Verifiable Rewards Can Match Frontier Agents
  21. 068
    The OS Trick That Makes Tree Search Practical for Coding Agents
  22. 061
    When Helpful Agents Go Sideways: A 404 Error, Campus Security, and Why Alignment Misses This
  23. 058
    Why Upgrading Your AI Auditor to a Smarter Model Can Make Your System Less Safe
  24. 057
    How Uber Caught 206 Leaked Credentials With an LLM-Powered Security Stack
  25. 053
    An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script
  26. 047
    When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
  27. 039
    When Smarter Agents Get Fooled by Three Extra Nodes in a Database
  28. 030
    Why Your AI Agent Won't Stop Working — and Each Model Falls for a Different Trap
  29. 029
    Why Forty-Eight Percent on FrontierMath Isn't the Real Story in DeepMind's New Math Paper
  30. 016
    Why Your Coding Agent Stalls While the GPU Runs Hot
  31. 003
    How to Pick the Best of Sixteen Coding Agent Rollouts

Related concepts

Related terms