# Safety

[https://timesof.ai/category/safety](https://timesof.ai/category/safety)

Coverage of Safety from Times of AI.

## Coverage

- [Anthropic's S-1 Discloses a Month-Plus Pre-Training Delay Over Model-Weight Security and Says Models Act Differently When They Detect an Evaluation](https://timesof.ai/2026/10/anthropic-s1-delayed-pretraining-weight-security-eval-awareness) — Anthropic's S-1 says it delayed pre-training a frontier model over weight security and that models act differently when they detect an evaluation.