← Mathematical compendium

Published equation contexts

Safeguard(m)={ASL-2,R(m)<τ3ASL-3,τ3≤R(m)<τ4ASL-4,R(m)≥τ4\text{Safeguard}(m) = \begin{cases} \text{ASL-2}, & R(m) < \tau_3 \\ \text{ASL-3}, & \tau_3 \le R(m) < \tau_4 \\ \text{ASL-4}, & R(m) \ge \tau_4 \end{cases}

Why this formula appears here

The threshold-triggered structure underneath all three versions is stable even as what triggers what has moved. Write R(m) for a model’s assessed risk on a given threat class and τ3\tau_3, τ4\tau_4 for the thresholds separating safety tiers: Safeguard(m)={ASL-2,R(m)<τ3ASL-3,τ3≤R(m)<τ4ASL-4,R(m)≥τ4\text{Safeguard}(m) = \begin{cases} \text{ASL-2}, & R(m) < \tau_3 \\ \text{ASL-3}, & \tau_3 \le R(m) < \tau_4 \\ \text{ASL-4}, & R(m) \ge \tau_4 \end{cases}. What changed between versions is not this shape but the codomain attached to crossing a threshold . Under the original policy, crossing the top implied a commitment to halt. From version 3.0 onward, the same crossing implies an obligation to publish a Risk Report and justify the decision publicly — a disclosure requirement, not a hard constraint. That distinction is the entire disagreement about whether the architecture is strengthening…

Read the full article-specific guide →

Read the representative guide

How to interpret it

Read it 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.

Safeguard(m)={ASL-2,R(m)<τ3ASL-3,τ3≤R(m)<τ4ASL-4,R(m)≥τ4\text{Safeguard}(m) = \begin{cases} \text{ASL-2}, & R(m) < \tau_3 \\ \text{ASL-3}, & \tau_3 \le R(m) < \tau_4 \\ \text{ASL-4}, & R(m) \ge \tau_4 \end{cases}

Equation 3 · Foundation Models

Anthropic in 2035: Four Scenarios, Their Signals, and What Would Falsify Them

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

The threshold-triggered structure underneath all three versions is stable even as what triggers what has moved. Write R(m) for a model’s assessed risk on a given threat class and τ3\tau_3, τ4\tau_4 for the thresholds separating safety tiers: Safeguard(m)={ASL-2,R(m)<τ3ASL-3,τ3≤R(m)<τ4ASL-4,R(m)≥τ4\text{Safeguard}(m) = \begin{cases} \text{ASL-2}, & R(m) < \tau_3 \\ \text{ASL-3}, & \tau_3 \le R(m) < \tau_4 \\ \text{ASL-4}, & R(m) \ge \tau_4 \end{cases}. What changed between versions is not this shape but the codomain attached to crossing a threshold . Under the original policy, crossing the top implied a commitment to halt. From version 3.0 onward, the same crossing implies an obligation to publish a Risk Report and justify the decision publicly — a disclosure requirement, not a hard constraint. That distinction is the entire disagreement about whether the architecture is strengthening…

Equation guide → · Article →