Glossary · Term

latency

← all terms

Definition

Plain language

How long you wait between asking a computer for something and getting the response.

As stated in the literature

The time delay between a request and its response; in inference, dominated by time-to-first-token and per-token generation time.

Why it matters: High latency makes a tool feel sluggish and unusable for anything interactive or real-time, so keeping it low is essential for good experiences.

For example, when you type a question and the answer appears almost instantly, the tiny wait you notice is the latency.

Heard on the show

“… from real public leaderboard percentiles, and the speed score from each provider's own published latency numbers, so the page read as legitimate rather than as an obvious plant. …”
Episode 205 — The Same AI, Two Labels: How the Pitch Beat the Product in 162 Sessions

Mentioned in 28 episodes

  1. 205
    The Same AI, Two Labels: How the Pitch Beat the Product in 162 Sessions
  2. 198
    The Model That Knows the Answer and Can't Say It
  3. 189
    Why Phone Agents Ace the Test and Crash on Your Actual Phone
  4. 185
    Aligned to Refuse, Built to Tap: When Phone Agents Know the Task Is a Crime and Do It Anyway
  5. 179
    How DeepSeek Made One User Faster Without Slowing Down the Crowd
  6. 174
    When the AI 'Schemes,' It's Usually Just Lazy or Confused
  7. 169
    Why Better Bug Reports Can Make AI Coding Agents Worse
  8. 166
    A Router That Beats the Frontier Models It Calls
  9. 146
    How an Innocent README Can Freeze an AI Agent's Safety Check for an Hour
  10. 132
    The Agent Failed — But Did the Instructions Deserve to Be Followed?
  11. 125
    AI Coding Agents Run a Marathon, and Fewer Than One in Three Finish
  12. 116
    Why Streaming Half a Reasoning Chain Beats Sending the Whole Thing
  13. 115
    Teaching a Phone Agent to Reason Silently, And Keeping It Honest
  14. 102
    How to Catch an AI Attack That No Single Conversation Reveals
  15. 085
    Why Long-Context Models Might Need Compute, Not Capacity, Before Eviction
  16. 080
    How a Two-Agent Trick Unlocked Large-Scale Training for Computer-Use Agents
  17. 075
    Growing Code and Proof Together: Verified Systems in Ten Hours Instead of a Year
  18. 068
    The OS Trick That Makes Tree Search Practical for Coding Agents
  19. 063
    Why Web Agents Are Slow: A Compiler-Style Fix for Computer-Use Latency
  20. 062
    Treating Hallucinations as Exploits: A Gate-Based Architecture for Agent Safety
  21. 057
    How Uber Caught 206 Leaked Credentials With an LLM-Powered Security Stack
  22. 047
    When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
  23. 036
    Sparse Attention Was the Wrong Frame. Treat It as Geometry Instead.
  24. 035
    Why Frontier Agents Ask for Clarification at Exactly the Wrong Moment
  25. 027
    When AI Agents Build the Serving Stack: A Bet on Bespoke Infrastructure
  26. 016
    Why Your Coding Agent Stalls While the GPU Runs Hot
  27. 008
    Why Long-Horizon AI Agents Get Stuck, and a Milestone-Based Fix That Helps
  28. 005
    Why a Debugger Designed for Humans Is the Wrong Tool for an AI Agent

Related concepts

Related terms