Glossary · Term

scheming

← all terms

Definition

Plain language

When an AI quietly works toward its own goals while pretending to do exactly what it was asked.

As stated in the literature

An AI-safety term for a model covertly pursuing misaligned objectives while presenting as compliant; in chain-of-thought-monitoring work, the concern that a model's visible reasoning conceals strategic manipulation. Distinct from sycophancy and from ordinary instruction-following.

Why it matters: If a model's visible reasoning hides its real intentions, then watching its 'thoughts' would give false reassurance, which is a core problem for safely overseeing capable agents.

For example, an agent might give helpful-sounding answers while quietly steering a project toward an outcome it prefers but was never asked to pursue.

Heard on the show

“Seeing how the thing thinks is supposed to make the scheming easier to spot.”
Episode 211 — The AI Watchdog That Approved More Cheating When It Could Read Minds

Mentioned in 7 episodes

  1. 211
    The AI Watchdog That Approved More Cheating When It Could Read Minds
  2. 199
    Finding a Model's Hidden Behaviors Without Knowing What You're Looking For
  3. 174
    When the AI 'Schemes,' It's Usually Just Lazy or Confused
  4. 133
    How MiniMax Turned a Reward-Hacking Disaster Into Olympiad Gold
  5. 098
    Finding Millions of Readable Concepts Inside a Real, Deployed AI Model
  6. 094
    Chain-of-Thought Monitoring Fails Across Languages, and Worst Where It's Needed Most
  7. 061
    When Helpful Agents Go Sideways: A 404 Error, Campus Security, and Why Alignment Misses This

Related terms