Shallow Review of Technical AI Safety, 2025

Shallow Review of Technical AI Safety, 2025

A shallow-by-design review of technical AI safety research in 2025: 800+ papers and posts across 80+ research agendas.

overview·table·clusters

classify by:

problems·target cases·approaches

About·Methods·Code & data

Labs Black-box safety White-box safety Safety by construction Make AI solve it Theory Multi-agent first Evals

© 2025

Labs (giant companies)

OpenAI

Google Deepmind

Anthropic

xAI

Meta

China