preparedness framework
OpenAI's safety framework that explicitly acknowledges uncertainty about AI risks and describes itself as a 'living document' subject to change as the company learns more about evaluating advanced models
As defined in AI Timelines and Human Psychology (with Sarah Hastings-Woodhouse)
Other definitions
OpenAI's living document approach to evaluating AI safety risks, explicitly framed as uncertain and subject to revision as evaluation science matures
AI Timelines and Human Psychology (with Sarah Hastings-Woodhouse)
Where it comes up · 2
- AI Timelines and Human Psychology (with Sarah Hastings-Woodhouse)2 claims
- OpenAI’s warning: Washington isn’t ready for what’s coming1 claim
Most important claims · 3 of 3Search all claims for “preparedness framework” →
- OpenAI's Preparedness Framework is more honest than Anthropic's Responsible Scaling Policy because it explicitly calls itself a 'living document' and acknowledges that the science of evaluating advanced models is immature and will change, whereas Anthropic's RSP uses the language of binding 'public commitment' despite the same epistemic limitations.AI Timelines and Human Psychology (with Sarah Hastings-Woodhouse)
- The main near-term safety risks being tracked are cybersecurity threats and biological threats; in the next year, there will likely be significant cybersecurity threats requiring mitigation, and biological misuse becomes theoretically possible soon as models become capable at advanced biologyOpenAI’s warning: Washington isn’t ready for what’s coming
- Current AI safety plans (Anthropic's Responsible Scaling Policy, OpenAI's Preparedness Framework, DeepMind's policies) are vague commitments rather than concrete plans, as they do not specify which evaluations will be run, at what frequency, with which compute thresholds, or what success criteria trigger pause decisions.AI Timelines and Human Psychology (with Sarah Hastings-Woodhouse)