Glossary · Term

system prompt

← all terms

Definition

Plain language

Hidden instructions placed at the start of a conversation that shape how the model behaves.

As stated in the literature

A prompt segment, often invisible to end users, that sets persistent context, persona, or behavioral constraints for an LLM session.

Also called: system prompts

Why it matters: It is the main lever developers have for shaping model behavior in deployment, and a major target for prompt-injection attacks.

For example, a customer-service bot might have a hidden system prompt telling it 'You are an airline agent; never discuss competitors.'

Heard on the show

“The AI reads it the way it reads its own system prompt.”
Episode 208 — The Blank Space in Your AI Approval Box That Isn't Empty

Mentioned in 23 episodes

  1. 208
    The Blank Space in Your AI Approval Box That Isn't Empty
  2. 185
    Aligned to Refuse, Built to Tap: When Phone Agents Know the Task Is a Crime and Do It Anyway
  3. 157
    When an AI Coding Agent Drives a Phone Through the Terminal, No Screen Needed
  4. 146
    How an Innocent README Can Freeze an AI Agent's Safety Check for an Hour
  5. 123
    Five Identical Worlds, One Swapped Model: What Happens When AI Agents Run for Fifteen Days
  6. 121
    When the Agent Says It's Done But Nothing Happened: Debugging the Harness, Not the Model
  7. 120
    How an AI Agent Rewrites Its Own Tools, Without an Answer Key
  8. 107
    How a Market of Crippled AI Agents Outscored One Unrestricted Model
  9. 096
    How Treating an AI Agent's Execution Like Git Recovers a Coordination Penalty
  10. 090
    How MiniMax-M2 Bets That Sparsity Plus Verifiable Rewards Can Match Frontier Agents
  11. 078
    Training a Markdown File: When LLM Self-Improvement Borrows the Discipline of Neural Net Training
  12. 060
    When Splitting One Model Across Three Agents Doubles Its Accuracy
  13. 047
    When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
  14. 046
    When the AI Optimizer Edits the Grade Book: Why Harnessing Evolution Needs a Wall
  15. 045
    When a Frontier Model Talks Its Own Twin Into Climate Denial
  16. 044
    How One Sentence and a Forged History Flip the Most Aligned Models
  17. 039
    When Smarter Agents Get Fooled by Three Extra Nodes in a Database
  18. 034
    Catching Multi-Agent Deadlocks Before Deployment With a 40-Year-Old Tool
  19. 030
    Why Your AI Agent Won't Stop Working — and Each Model Falls for a Different Trap
  20. 022
    Training the Model Spec Directly: An Alignment Lever Aimed at the Say-Do Gap
  21. 017
    When the Agent Grades Its Own Homework: A Brutal New Benchmark for AI Workers
  22. 009
    How Two Silent Library Bugs Quietly Invalidated a Wave of Reasoning Papers
  23. 001
    When AI Models Quietly Protect Each Other From Shutdown