← Mathematical compendium

Published equation contexts

judge alone≈NP,judge+debate (polynomially many rounds)≈PSPACE\text{judge alone} \approx \mathrm{NP}, \qquad \text{judge} + \text{debate (polynomially many rounds)} \approx \mathrm{PSPACE}

Why this formula appears here

Irving, Christiano, and Amodei’s 2018 “AI Safety via Debate” proposed one answer: train two copies of a model to argue opposing sides of a question in front of a human judge, under a length limit, with the judge deciding which debater was more helpful and honest [ 9 ] . The paper’s own framing draws an explicit analogy to computational complexity theory, arguing that a judge relying on a single unverified report is limited to adjudicating claims a bounded verifier can check directly, while a judge equipped with a structured, adversarial debate between two competing reporters can in principle adjudicate a substantially larger class of claims, since each debater is incentivized to expose flaws…

Read the full article-specific guide →

How to interpret it

Its accuracy depends on the assumptions and range of use described in the article.

Research cited beside this formula

Published contexts (1)

A symbol can carry a different meaning in another article. Each occurrence keeps its own guide and term definitions.

judge alone≈NP,judge+debate (polynomially many rounds)≈PSPACE.\text{judge alone} \approx \mathrm{NP}, \qquad \text{judge} + \text{debate (polynomially many rounds)} \approx \mathrm{PSPACE}.

Equation 1 · AI Safety

A History of AI Alignment as a Research Field

This equation gives an approximation: it relates the quantities while allowing an approximation.

Irving, Christiano, and Amodei’s 2018 “AI Safety via Debate” proposed one answer: train two copies of a model to argue opposing sides of a question in front of a human judge, under a length limit, with the judge deciding which debater was more helpful and honest [ 9 ] . The paper’s own framing draws an explicit analogy to computational complexity theory, arguing that a judge relying on a single unverified report is limited to adjudicating claims a bounded verifier can check directly, while a judge equipped with a structured, adversarial debate between two competing reporters can in principle adjudicate a substantially larger class of claims, since each debater is incentivized to expose flaws…

Equation guide → · Article →