The framework outlines seven principles for evaluating catastrophic risk scenarios
Miles Brundage#57
1/ New from @GuidelightAI : standards for AI capability testing, built around 7 principles for measuring the abilities of an AI system relevant to catastrophic risk.
Users are excited about GuidelightAI releasing its V1.0 standard for AI capability testing on catastrophic risks.
No Digg Deeper questions have been answered for this story yet.
Strong testing is the bedrock that so many other AI safety practices depend on
We've just published @GuidelightAI's v1.0 standard for it; let us know what you think!
1/ New from @GuidelightAI : standards for AI capability testing, built around 7 principles for measuring the abilities of an AI system relevant to catastrophic risk.
Read our full Capability Testing standard here: http://guidelight.ai/capability-testing
Strong testing is the bedrock that so many other AI safety practices depend on
We've just published @GuidelightAI's v1.0 standard for it; let us know what you think!
@teganmccaslin2 @GuidelightAI Excited to have this out!
2/ Read the full standard at our site: https://guidelight.ai/capability-testing
Strong testing is the bedrock so that many other AI safety practices depend on
We've just published @GuidelightAI 's v1.0 standard for it; let us know what you think!
1/ New from @GuidelightAI : standards for AI capability testing, built around 7 principles for measuring the abilities of an AI system relevant to catastrophic risk.
Read our full Capability Testing standard here: https://www.guidelight.ai/capability-testing
Strong testing is the bedrock so that many other AI safety practices depend on
We've just published @GuidelightAI 's v1.0 standard for it; let us know what you think!