← All organizations

Vector Institute: AI trust & safety

University institute or centre · Toronto, ON, Canada

Alignment & controlEvaluations & benchmarksSecurity & robustnessGovernance & policyEthics & societal impact

Independent frontier-model evaluations (2025: benchmarked 11 LLMs), adversarial robustness, trustworthy ML, trust/safety policy. Weighted toward evals and governance rather than deep alignment.

Website

https://vectorinstitute.ai

People

Roger Grosse (Faculty Member; also at Anthropic), David Duvenaud (founding member)

Founded

2017 (institute)

Source

https://aisecurityandsafety.org/en/organizations/

Confidence

unverified (doc) Inherited from an earlier internal document and not yet re-checked.

Something wrong? Email us.