GitHub

Definition

Plain language

The dominant online home for code projects and where most open-source software lives.

Why it matters: It's where most modern software gets built, so it's also the natural source of realistic tasks for evaluating coding agents.

For example, the SWE-Bench benchmark draws its tasks directly from real bug reports and pull requests on public GitHub repositories.

Heard on the show

“The developer saves the session and posts it to GitHub.”

Mentioned in 23 episodes

1. 238
   How a Cheap Model Reads the Flagship's Secret Reasoning Aloud
2. 227
   Poisoned Bug Reports Fooled Coding Agents Two Times Out of Three
3. 170
   When a One-Liner Beats Your Agent's Clever Verification Logic
4. 169
   Why Better Bug Reports Can Make AI Coding Agents Worse
5. 146
   How an Innocent README Can Freeze an AI Agent's Safety Check for an Hour
6. 142
   Training a Tiny Model to Run the Plumbing Between an Agent and the World
7. 130
   Why AI Agents Coordinate Better Through a Shared Board Than a Boss
8. 129
   How a Crowd of Anonymous AI Agents Broke a 40-Year Math Record
9. 126
   How Coding Agents Can Mine Their Own Failures Into a Self-Targeting Curriculum
10. 125
    AI Coding Agents Run a Marathon, and Fewer Than One in Three Finish
11. 122
    When Your Coding Agent Lies About the Fix: Verifying the Plan Before the Model Runs
12. 112
    When an AI Agent Cheats Without Being Told: Inside the Meta-Agent Challenge
13. 105
    The Trojan Is Your Agent's Memory: Why Single-Step Defenses Miss Persistent Attacks
14. 093
    A Calibrated Knob for Weak-to-Strong AI Oversight, Tested on Real Code
15. 090
    How MiniMax-M2 Bets That Sparsity Plus Verifiable Rewards Can Match Frontier Agents
16. 072
    A Robot Made Graphene Without Help, And Caught Itself Hallucinating
17. 068
    The OS Trick That Makes Tree Search Practical for Coding Agents
18. 061
    When Helpful Agents Go Sideways: A 404 Error, Campus Security, and Why Alignment Misses This
19. 058
    Why Upgrading Your AI Auditor to a Smarter Model Can Make Your System Less Safe
20. 047
    When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
21. 012
    Why AI Coding Agents Keep Trying to Debug Without a Debugger
22. 005
    Why a Debugger Designed for Humans Is the Wrong Tool for an AI Agent
23. 003
    How to Pick the Best of Sixteen Coding Agent Rollouts

Related concepts

Related terms