Glossary · Term

heads-up

← all terms

Definition

Plain language

Poker played one-on-one, just two players at the table.

As stated in the literature

In poker, a two-player (one-versus-one) format; heads-up no-limit Texas Hold'em is the standard testbed for poker AI such as Libratus and PokerSkill.

Also called: heads up

Why it matters: It matters because the one-on-one setting is the cleanest stage for testing an AI's strategy under hidden information.

For example, when a poker tournament narrows down to its final two players, they play heads-up until one has all the chips.

Heard on the show

“Quick heads up before we start — this is an AI-made explainer, both voices included.”
Episode 217 — Why an AI Called Fourteen Broken Figures Perfect, And What It Reveals About Test-Time Compute

Mentioned in 46 episodes

  1. 217
    Why an AI Called Fourteen Broken Figures Perfect, And What It Reveals About Test-Time Compute
  2. 216
    The AI Tutor That Gives Poor Kids a Thinner History
  3. 215
    The Same Policy Scored 85 for the US and 36 for Russia
  4. 214
    The Medical AI Answer That's Accurate, Sourced, and Still Wrong
  5. 213
    A Model Learned to Control a Robot by Watching Video It Never Acted On
  6. 212
    The Fact Was in the Wrong Drawer: Why Fine-Tuned Models Can't Reason With What They Know
  7. 211
    The AI Watchdog That Approved More Cheating When It Could Read Minds
  8. 210
    Same Website Request, Different Code — The Bias You Can't See
  9. 209
    How 2.6 Billion Doodles Exposed the Culture Words Quietly Delete
  10. 208
    The Blank Space in Your AI Approval Box That Isn't Empty
  11. 207
    An AI Graded Its Own Math Test 94 Percent — It Actually Scored 20
  12. 202
    How Do You Know an AI Agent Actually Refused? Check the World, Not the Words
  13. 194
    How a Robot Builds a Debugging Notebook It Can Read, Edit, and Hand to Another Robot
  14. 193
    Freeze Most of the Network: Where RL Improvement Actually Lives in a Transformer
  15. 192
    A 32B Open Model Matched Frontier Systems By Learning to Take Notes
  16. 191
    How One Researcher Beat GPT-5.2 and Gemini 3 by Judging Their Answers, Not Improving Them
  17. 190
    The Skill Every AI Manager Is Missing: Handing Out Exactly the Right Keys
  18. 189
    Why Phone Agents Ace the Test and Crash on Your Actual Phone
  19. 188
    A Coding Agent Found a Hole in a Peer-Reviewed STOC Proof for Five Dollars
  20. 187
    An 8-Billion Agent That Beats Models 80 Times Its Size By Looking Things Up
  21. 186
    How a Frozen Model Went From 2% to 77% on Physics Puzzles — Without Retraining
  22. 185
    Aligned to Refuse, Built to Tap: When Phone Agents Know the Task Is a Crime and Do It Anyway
  23. 184
    An AI Built an Undetectable Secret Channel, And Another AI Couldn't Find It
  24. 183
    Why You Can't Fine-Tune Foresight Into an AI Agent
  25. 182
    How a Tiny Model Too Weak to Plan Cuts a Bigger Agent's Hallucinations by 80%
  26. 181
    How to Backpropagate Blame Through a Team of Chatbots — And When It Backfires
  27. 179
    How DeepSeek Made One User Faster Without Slowing Down the Crowd
  28. 178
    How an AI Reviewer Learned to Stop Going Easy on AI Writing
  29. 177
    Why Raw Profiler Data Made an AI Worse at Writing GPU Code
  30. 176
    An AI Designed Its Own Psychology Studies, Then Confirmed What It Found
  31. 175
    One Crosscoder Feature Flips a Stalling Chatbot Into a Working Agent
  32. 174
    When the AI 'Schemes,' It's Usually Just Lazy or Confused
  33. 173
    The Free Step-Level Grader Hiding in Every RL Training Run
  34. 172
    One Bad Token Can Sink a Model's Math, And You Can Delete It
  35. 171
    The Safety Decision a Model Makes Before It Thinks a Word
  36. 170
    When a One-Liner Beats Your Agent's Clever Verification Logic
  37. 169
    Why Better Bug Reports Can Make AI Coding Agents Worse
  38. 168
    When Turning Experience Into Code Makes Your AI Agent Dumber
  39. 167
    How Teaching an AI to Predict, Not Act, Made It a Better Actor
  40. 166
    A Router That Beats the Frontier Models It Calls
  41. 165
    A Free-Lunch Tweak That Lets a Tiny Agent Beat Frontier Giants
  42. 164
    The Summarizer That Quietly Deletes Your Agent's Safety Rules
  43. 163
    Why Training Only on Perfect Solutions Cripples a Model's Reasoning
  44. 162
    The Empty-Lake Proof: Why More Rollouts Stop Helping Reasoning Models
  45. 150
    Don't Kill the Loser: A Different Way to Handle Two AI Agents Colliding
  46. 100
    How a Prompt Wrapper Lets a Frontier Model Play Poker Like an Expert

Related terms

Libratus PokerSkill Texas Hold'em