← Mathematical compendium

Published equation contexts

C(model)≥τk  ⟹  deploy only if safeguards≥SkC(\text{model}) \ge \tau_k \;\Longrightarrow\; \text{deploy only if safeguards} \ge S_k

Why this formula appears here

The policy’s structure is what makes it useful to state formally, because its core mechanism is a conditional commitment rather than a fixed rule. Anthropic defines AI Safety Levels (ASL), each tied to a capability threshold on a specific class of risk — most concretely, the potential for a model to meaningfully assist in acquiring chemical, biological, radiological, or nuclear weapons capability, or to self-exfiltrate or resist correction. The policy’s operating logic, stripped to its structural claim, is a threshold trigger: C(model)≥τk  ⟹  deploy only if safeguards≥SkC(\text{model}) \ge \tau_k \;\Longrightarrow\; \text{deploy only if safeguards} \ge S_k. where C(model\text{model}) is the model’s evaluated capability on a specific threat class, τk\tau_k is the threshold defining ASL level k , and SkS_k is…

Read the full article-specific guide →

Read the representative guide

How to interpret it

Read this expression with the definitions, units, and assumptions supplied by the article.

Research cited beside this formula

Learn the mathematics behind it

Published contexts (1)

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

C(model)≥τk  ⟹  deploy only if safeguards≥Sk,C(\text{model}) \ge \tau_k \;\Longrightarrow\; \text{deploy only if safeguards} \ge S_k,

Equation 1 · Foundation Models

A History of Anthropic and the Claude Model Line

This equation states a bound: one expression must stay on the indicated side of the other under the article’s assumptions.

The policy’s structure is what makes it useful to state formally, because its core mechanism is a conditional commitment rather than a fixed rule. Anthropic defines AI Safety Levels (ASL), each tied to a capability threshold on a specific class of risk — most concretely, the potential for a model to meaningfully assist in acquiring chemical, biological, radiological, or nuclear weapons capability, or to self-exfiltrate or resist correction. The policy’s operating logic, stripped to its structural claim, is a threshold trigger: C(model)≥τk  ⟹  deploy only if safeguards≥SkC(\text{model}) \ge \tau_k \;\Longrightarrow\; \text{deploy only if safeguards} \ge S_k. where C(model\text{model}) is the model’s evaluated capability on a specific threat class, τk\tau_k is the threshold defining ASL level k , and SkS_k is…

Meanings in this article

  • CC: the model’s evaluated capability on a specific threat class.
  • τk\tau_k: the threshold defining ASL level k.
  • SkS_k: the security and deployment standard the policy requires once that threshold is crossed.
Equation guide → · Article →