Model Evaluation for Extreme Risks

What it is

Argues that before release, labs should test models for dangerous capabilities and for whether they will apply them — and sets out what responsible release decisions would look like. Free on arXiv.

Why I recommend it

This is where today's “frontier safety framework” language comes from. Written largely by the labs it would govern, which is worth holding in mind.

Topics

#ai ethics #ai-ethics #free #paper #reading #research #technology-and-ethics

Added Sep 19, 2026 · 0 opens