Ask what should change when the equation is manipulated, then let the visualization test that expectation.
Foundation Lab
Sandwiching Evaluations
Makes scalable oversight empirically testable today
#94SandwichScaling & Alignment
key equation
\text{Score} = \frac{P_{H+A} - P_H}{P_E - P_H}Selected Foundation Object
Keep the equation fixed; move through the evidence.
Concept 94 of 100SandwichScaling & Alignment / Phase 12: Advanced alignment & safety research
Current question
Bottom = unaided human, top = expert, middle = AI-assisted human
\text{Score} = \frac{P_{H+A} - P_H}{P_E - P_H}Use the runnable panel, the key equation, and canonical papers as separate forms of evidence for the same object.
The useful learning product is the reusable mechanism you can carry into another model, paper, or engineering tradeoff.
Use prerequisites, dependents, and semantic links to repair the next gap without leaving the object behind.
Why It Matters for Modern Models
- Makes scalable oversight empirically testable today
- Choose tasks where experts can judge, non-experts struggle
- Proxy for future "smart model oversight" capabilities
What Tutorials Skip
What is still poorly explained in textbooks and papers:
- Bottom = unaided human, top = expert, middle = AI-assisted human
- Tests: can weaker oversight + AI match stronger oversight?
- Foundational benchmark for alignment research progress
Interactive Visualization
Core Math (Optional Deep Dive)
If you want intuition first, start with the key equation and the visualization. Come back here for the full walkthrough.
Key Equation
Sandwich score measures AI-assisted oversight:
- : non-expert performance
- : non-expert + AI assistance
- : expert performance
Score = 1.0 means assisted non-expert matches expert.