Glossary · Term

fork

← all terms

Definition

Plain language

A standard Unix command that instantly duplicates a running program by sharing its memory until one of the copies changes something.

As stated in the literature

The Unix system call that creates a child process sharing the parent's memory pages copy-on-write; central to DeltaBox's millisecond-scale memory snapshots and to standard RL fan-out for agent training.

Also called: fork()

Why it matters: It's the foundation of cheap parallel sandboxes, which is how RL pipelines and snapshotting systems achieve fast fan-out without duplicating gigabytes.

For example, a parent process can fork into a thousand children almost instantly because they all share the same memory pages until one tries to write.

Heard on the show

“And the lifecycle: roster edits every ten tasks — fork a winner, merge near-duplicates, prune dead weight, spawn a fresh specialist for uncovered task types.”
Episode 200 — The One Mechanism That Turns Twenty AI Clones Into an Actual Team

Mentioned in 29 episodes

  1. 200
    The One Mechanism That Turns Twenty AI Clones Into an Actual Team
  2. 196
    AI Agents Reached Opposite Conclusions From the Same Data — and Passed Review
  3. 187
    An 8-Billion Agent That Beats Models 80 Times Its Size By Looking Things Up
  4. 185
    Aligned to Refuse, Built to Tap: When Phone Agents Know the Task Is a Crime and Do It Anyway
  5. 184
    An AI Built an Undetectable Secret Channel, And Another AI Couldn't Find It
  6. 182
    How a Tiny Model Too Weak to Plan Cuts a Bigger Agent's Hallucinations by 80%
  7. 181
    How to Backpropagate Blame Through a Team of Chatbots — And When It Backfires
  8. 178
    How an AI Reviewer Learned to Stop Going Easy on AI Writing
  9. 172
    One Bad Token Can Sink a Model's Math, And You Can Delete It
  10. 168
    When Turning Experience Into Code Makes Your AI Agent Dumber
  11. 163
    Why Training Only on Perfect Solutions Cripples a Model's Reasoning
  12. 162
    The Empty-Lake Proof: Why More Rollouts Stop Helping Reasoning Models
  13. 154
    How a 7B Model Out-Investigates a 72B One by Choosing What to Look At
  14. 150
    Don't Kill the Loser: A Different Way to Handle Two AI Agents Colliding
  15. 129
    How a Crowd of Anonymous AI Agents Broke a 40-Year Math Record
  16. 119
    Beating Reinforcement Learning Without Ever Touching the Model's Weights
  17. 117
    How an Open AI System Verified 672 Hard Math Proofs for Under $300
  18. 116
    Why Streaming Half a Reasoning Chain Beats Sending the Whole Thing
  19. 113
    What If a Prompt Injection Never Left? Attacks That Wait in Agent Memory
  20. 111
    How a 4B Web Agent Beat Models 60x Its Size on 500 Demonstrations
  21. 096
    How Treating an AI Agent's Execution Like Git Recovers a Coordination Penalty
  22. 091
    When Better Fine-Tuning Can't Help: A Geometric Impossibility in LLM Causal Reasoning
  23. 080
    How a Two-Agent Trick Unlocked Large-Scale Training for Computer-Use Agents
  24. 068
    The OS Trick That Makes Tree Search Practical for Coding Agents
  25. 066
    Why Giving an AI Agent More Tools Can Make It Worse at Using a Computer
  26. 042
    An Agentic Scientific Computing System That Actually Remembers What It Learns
  27. 026
    What RL Actually Does to Language Models, at the Token Level
  28. 023
    Why a Small Agent Confidently Overwrites Memories It Doesn't Understand
  29. 016
    Why Your Coding Agent Stalls While the GPU Runs Hot

Related terms