AI models can be dangerous before public deployment - METR
metr.org · 1,316 words · saved by 2 readers
Why pre-deployment testing is not an adequate framework for AI risk management
Many frontier AI safety policies from scaling labs (e.g. OpenAI’s Preparedness Framework, Google DeepMind’s Frontier Safety Framework, etc.), as well as past work by third party evaluators including UK AISI, Apollo Research, and METR, focus on pre-deployment testing – ensuring that the AI model is safe and that the lab has sufficient security before the lab deploys the model to the public. Such pre-deployment safety evaluations are standard for a wide variety of products across many industries, where the primary risk of the product is to the consumer (see, for example, the crash testing…
saved by
related reading
- Common Elements of Frontier AI Safety Policiesmetr.org
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- A Safe Path to Open Weights - Thinking Machines Labthinkingmachines.ai
- Emerging processes for frontier AI safety - GOV.UKgov.uk
- AI catastrophes and rogue deployments - by Buck Shlegerisblog.redwoodresearch.org
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- Predicting LLM Safety Before Release by Simulating Deploymentcdn.openai.com
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- AI in 2025: gestalt — LessWronglesswrong.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- AI safety is not a model propertysubstack.com
- Off Target | CNAScnas.org