one-shot

Definition

Plain language

Getting one attempt, with no examples and no second pass.

Also called: one shot, one-shot authoring

Why it matters: One-shot results show what a model can do unaided, which is the setting most real users are in when they paste a prompt and take the first answer.

For example, a one-shot request is asking the model to write a full test suite in a single reply, with no sample suites to imitate and no chance to revise it.

Heard on the show

“Everything you've heard so far is one-shot authoring with test-time reasoning switched off.”

Mentioned in 30 episodes

1. 233
   Why a Model Can Grade an Answer But Not Write the Answer Key
2. 208
   The Blank Space in Your AI Approval Box That Isn't Empty
3. 179
   How DeepSeek Made One User Faster Without Slowing Down the Crowd
4. 177
   Why Raw Profiler Data Made an AI Worse at Writing GPU Code
5. 173
   The Free Step-Level Grader Hiding in Every RL Training Run
6. 159
   Can a Coding Agent Run Its Own Robot Experiments Overnight, With No Human Resetting the Scene?
7. 157
   When an AI Coding Agent Drives a Phone Through the Terminal, No Screen Needed
8. 154
   How a 7B Model Out-Investigates a 72B One by Choosing What to Look At
9. 143
   When a Model Notices You Forged Its Own Words, And Why That Breaks Safety Tests
10. 141
    How Two Tokens Reopened a Reasoning Method the Field Had Given Up On
11. 133
    How MiniMax Turned a Reward-Hacking Disaster Into Olympiad Gold
12. 124
    A Cheap Model With the Blueprints Beats Expensive Models Working Blind
13. 123
    Five Identical Worlds, One Swapped Model: What Happens When AI Agents Run for Fifteen Days
14. 120
    How an AI Agent Rewrites Its Own Tools, Without an Answer Key
15. 105
    The Trojan Is Your Agent's Memory: Why Single-Step Defenses Miss Persistent Attacks
16. 104
    How Making a Research Agent Smarter Quietly Makes It Leak Your Secrets
17. 090
    How MiniMax-M2 Bets That Sparsity Plus Verifiable Rewards Can Match Frontier Agents
18. 088
    Two Levers for Self-Improving AI: When Rewriting Code Isn't Enough
19. 082
    Training a Deep Research Agent on 8,000 Synthetic Tasks: The Rubric Tree Trick
20. 075
    Growing Code and Proof Together: Verified Systems in Ten Hours Instead of a Year
21. 066
    Why Giving an AI Agent More Tools Can Make It Worse at Using a Computer
22. 060
    When Splitting One Model Across Three Agents Doubles Its Accuracy
23. 053
    An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script
24. 046
    When the AI Optimizer Edits the Grade Book: Why Harnessing Evolution Needs a Wall
25. 042
    An Agentic Scientific Computing System That Actually Remembers What It Learns
26. 035
    Why Frontier Agents Ask for Clarification at Exactly the Wrong Moment
27. 029
    Why Forty-Eight Percent on FrontierMath Isn't the Real Story in DeepMind's New Math Paper
28. 016
    Why Your Coding Agent Stalls While the GPU Runs Hot
29. 013
    Why Search Keeps Rediscovering the Same Workflow, and What That Means
30. 011
    When RL Actually Teaches Agents Something New, And When It Doesn't

Related concepts

Related terms