AI Safety

Before I trust a safety strategy at scale, I want to see documented risks, recurring eval coverage, named owners for mitigations, and a record of at least a few launch or scope decisions that changed because of the findings. That is what separates a safety practice from a safety posture deck.

I care less about a single composite safety score than whether the program catches severe failures before release, how fast mitigations ship after a finding, and whether the high-risk tasks are actually covered by recurring evaluations. Before I trust a safety strategy at scale, I want to see documented risks, recurring eval coverage, named owners for mitigations, and a record of at least a few launch or scope decisions that changed because of the findings. That is what separates a safety practice from a safety posture deck.

The clearest signals usually live in clarity of the threat model, repeatability of the evaluation process, and evidence that the findings change deployment choices. A good archive helps future-you compare decisions over time instead of restarting each month from a vague sense that things are improving.

Keep these nearby while you evaluate:
- Inspect documentation: inspect.aisi.org.uk/
One of the best places to see evaluation design turned into runnable workflows.
- AI RMF Playbook: airc.nist.gov/AI_RMF_Knowledge_Base/Playbook
The most useful NIST material when a team needs implementation moves, not just principles.
- Anthropic video archive: youtube.com/@AnthropicAI/videos
Talks and interviews that help connect research language to deployment reality.