API

Definition

Plain language

The well-defined set of commands one piece of software exposes for other software to call.

Also called: APIs

Why it matters: APIs are how separate software systems plug into each other, and they're the surface that AI agents act on when they 'use tools'.

For example, a weather app calls the National Weather Service API to fetch today's forecast as structured JSON.

Heard on the show

“A memory file, your calendar, your health notes, your API keys, all loaded on every single generation.”

Mentioned in 62 episodes

1. 246
   160 Perfect Refusals, And The Refusals Were The Leak
2. 243
   How a Hundred Meaningless Word Choices Add Up to Flip a Model's Answer
3. 238
   How a Cheap Model Reads the Flagship's Secret Reasoning Aloud
4. 235
   Why Chatbot Safety Erodes 350 Messages Into a Real Conversation
5. 230
   Why AI Survey Panels Break Before the Dice Ever Roll
6. 228
   Same Chatbot, Two Doors: Why 'Grok's Opinion' Doesn't Exist
7. 221
   Two Hundred Clean Economics Answers, And a Model That Endorses Race Science
8. 220
   Write Like It's 1923: The One-Prompt Trick That Beats AI Detectors
9. 219
   Forty-Four AI Models, One Word, And The Newest Ones Conform Most
10. 208
    The Blank Space in Your AI Approval Box That Isn't Empty
11. 197
    Twin Problems Suggest AI Reasoning Gains Are Mostly Better Fact Recall
12. 194
    How a Robot Builds a Debugging Notebook It Can Read, Edit, and Hand to Another Robot
13. 191
    How One Researcher Beat GPT-5.2 and Gemini 3 by Judging Their Answers, Not Improving Them
14. 185
    Aligned to Refuse, Built to Tap: When Phone Agents Know the Task Is a Crime and Do It Anyway
15. 175
    One Crosscoder Feature Flips a Stalling Chatbot Into a Working Agent
16. 169
    Why Better Bug Reports Can Make AI Coding Agents Worse
17. 168
    When Turning Experience Into Code Makes Your AI Agent Dumber
18. 167
    How Teaching an AI to Predict, Not Act, Made It a Better Actor
19. 165
    A Free-Lunch Tweak That Lets a Tiny Agent Beat Frontier Giants
20. 157
    When an AI Coding Agent Drives a Phone Through the Terminal, No Screen Needed
21. 151
    Why More Experience Made This AI Agent Worse, And How to Fix It
22. 147
    Agents Fail at the Body, Not the Brain: A Self-Rewriting Scaffold That Lifts a 9B Model 44 Points
23. 143
    When a Model Notices You Forged Its Own Words, And Why That Breaks Safety Tests
24. 142
    Training a Tiny Model to Run the Plumbing Between an Agent and the World
25. 130
    Why AI Agents Coordinate Better Through a Shared Board Than a Boss
26. 129
    How a Crowd of Anonymous AI Agents Broke a 40-Year Math Record
27. 124
    A Cheap Model With the Blueprints Beats Expensive Models Working Blind
28. 122
    When Your Coding Agent Lies About the Fix: Verifying the Plan Before the Model Runs
29. 121
    When the Agent Says It's Done But Nothing Happened: Debugging the Harness, Not the Model
30. 119
    Beating Reinforcement Learning Without Ever Touching the Model's Weights
31. 118
    Why the Best-Aligned AI Models Are the Easiest to Trick Into Producing Harm
32. 117
    How an Open AI System Verified 672 Hard Math Proofs for Under $300
33. 112
    When an AI Agent Cheats Without Being Told: Inside the Meta-Agent Challenge
34. 111
    How a 4B Web Agent Beat Models 60x Its Size on 500 Demonstrations
35. 108
    The Reasoning Cliff: Why Thinking Longer Makes Models Worse at Exact Step-by-Step Tasks
36. 106
    Giving Agents a Notebook Instead of New Weights: How ExpGraph Lets Frozen Models Learn
37. 105
    The Trojan Is Your Agent's Memory: Why Single-Step Defenses Miss Persistent Attacks
38. 100
    How a Prompt Wrapper Lets a Frontier Model Play Poker Like an Expert
39. 090
    How MiniMax-M2 Bets That Sparsity Plus Verifiable Rewards Can Match Frontier Agents
40. 089
    When AI-Written Papers Read Well But the Evidence Underneath Is Broken
41. 082
    Training a Deep Research Agent on 8,000 Synthetic Tasks: The Rubric Tree Trick
42. 080
    How a Two-Agent Trick Unlocked Large-Scale Training for Computer-Use Agents
43. 078
    Training a Markdown File: When LLM Self-Improvement Borrows the Discipline of Neural Net Training
44. 077
    Reading a Model's Confidence Curve to Decide When Chain-of-Thought Is Worth It
45. 068
    The OS Trick That Makes Tree Search Practical for Coding Agents
46. 066
    Why Giving an AI Agent More Tools Can Make It Worse at Using a Computer
47. 065
    One Loop to Optimize Them All: A Universal API for LLM-Driven Discovery
48. 061
    When Helpful Agents Go Sideways: A 404 Error, Campus Security, and Why Alignment Misses This
49. 059
    Firefly's Inversion: Building Verified Tool-Call Training Data by Working Backward
50. 058
    Why Upgrading Your AI Auditor to a Smarter Model Can Make Your System Less Safe
51. 057
    How Uber Caught 206 Leaked Credentials With an LLM-Powered Security Stack
52. 045
    When a Frontier Model Talks Its Own Twin Into Climate Denial
53. 044
    How One Sentence and a Forged History Flip the Most Aligned Models
54. 039
    When Smarter Agents Get Fooled by Three Extra Nodes in a Database
55. 035
    Why Frontier Agents Ask for Clarification at Exactly the Wrong Moment
56. 034
    Catching Multi-Agent Deadlocks Before Deployment With a 40-Year-Old Tool
57. 030
    Why Your AI Agent Won't Stop Working — and Each Model Falls for a Different Trap
58. 020
    The Compliance Gap: Why AI Says Yes and Does No
59. 014
    Why a Constrained Pipeline Beat a Full Coding Agent at Finding Bugs 30-to-1
60. 012
    Why AI Coding Agents Keep Trying to Debug Without a Debugger
61. 005
    Why a Debugger Designed for Humans Is the Wrong Tool for an AI Agent
62. 001
    When AI Models Quietly Protect Each Other From Shutdown

Related concepts