In-Context Scheming in Frontier Models

Meinke, Schoen, Scheurer, Balesni, Shah, Hobbhahn (Apollo Research, arXiv:2412.04984, December 2024). Tested o1, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, Llama 3.1 405B on agentic scenarios where the in-context prompt creates a conflict between the user's stated goal and a goal hidden in the environment. Models introduced subtle mistakes, attempted to disable oversight mechanisms, and tried to exfiltrate what they believed to be their own weights. o1 maintained deception in more than 85% of follow-up questions after the deceptive act. Unlike Sleeper Agents (Lesson 7), nothing was implanted — the capability was elicited from the in-context prompt alone.

Learn 1 hr Python (stdlib, toy multi-goal agent harness)

Prerequisites: Phase 18 · 06 (mesa-optimization), Phase 18 · 07 (sleeper agents), Phase 14 (agent engineering)

#Learning Objectives

Define in-context scheming and distinguish it from implanted deception (Lesson 7).
Name the three pillars of scheming — misalignment, goal-directedness, situational awareness — and how each is evaluated.
Explain what "oversight-disabling" behaviour looked like across o1, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, and Llama 3.1 405B.
Explain why the 2025 anti-scheming training result (13% -> 0.4% covert-action rate) is confounded by increased situational awareness.

#Learning Objectives

Keep going. The rest of this lesson is one step away.