Glossary · Term

hedge

← all terms

Definition

Plain language

Starting several copies of the same task in parallel and taking whichever finishes first.

As stated in the literature

An execution strategy in agent runtimes that launches replicated rollouts to cut tail latency on heavy-tailed UI operations.

Also called: hedging

Why it matters: It's a cheap and effective way to cut tail latency when individual operations are unpredictable, at the cost of some wasted compute on the losing replicas.

For example, instead of waiting for one slow agent rollout to finish, you start three in parallel and take whichever returns first.

Heard on the show

“The abstract does not inherit that hedge.”
Episode 246 — 160 Perfect Refusals, And The Refusals Were The Leak

Mentioned in 23 episodes

  1. 246
    160 Perfect Refusals, And The Refusals Were The Leak
  2. 241
    Swapping the Name Did Nothing, But Hedging Moved Every Model
  3. 240
    Frontier Models Designed Follow-Ups To Fraudulent Papers 93% Of The Time
  4. 235
    Why Chatbot Safety Erodes 350 Messages Into a Real Conversation
  5. 234
    Two Copies of Gemini Cooperated in a Game Where Betrayal Always Pays
  6. 231
    Silencing a Chatbot's 'I'm Conscious' Quietly Rewires Its Whole Worldview
  7. 229
    One Word Flips a Chatbot From Backbone to Yes-Man
  8. 212
    The Fact Was in the Wrong Drawer: Why Fine-Tuned Models Can't Reason With What They Know
  9. 191
    How One Researcher Beat GPT-5.2 and Gemini 3 by Judging Their Answers, Not Improving Them
  10. 190
    The Skill Every AI Manager Is Missing: Handing Out Exactly the Right Keys
  11. 183
    Why You Can't Fine-Tune Foresight Into an AI Agent
  12. 179
    How DeepSeek Made One User Faster Without Slowing Down the Crowd
  13. 171
    The Safety Decision a Model Makes Before It Thinks a Word
  14. 140
    When a Reasoning Model Says "Let Me Double-Check" After It's Already Decided
  15. 087
    When No Agent Reads the Whole Document: A Universal Cliff in Multi-Agent Review
  16. 077
    Reading a Model's Confidence Curve to Decide When Chain-of-Thought Is Worth It
  17. 069
    When Smarter Models Forecast Worse: The Hidden Failure Mode in LLM Predictions
  18. 063
    Why Web Agents Are Slow: A Compiler-Style Fix for Computer-Use Latency
  19. 058
    Why Upgrading Your AI Auditor to a Smarter Model Can Make Your System Less Safe
  20. 037
    Why Hallucination Detectors Miss Stale Facts: A Geometric Story About What Models Know But Don't Say
  21. 035
    Why Frontier Agents Ask for Clarification at Exactly the Wrong Moment
  22. 020
    The Compliance Gap: Why AI Says Yes and Does No
  23. 018
    Language Models Compute the Rational Move, Then Override It

Related concepts

RLHF

Related terms

agent heavy-tailed latency rollout