Yoshua Bengio: International AI Safety Report, Catastrophic Risks, and Scientist AI
[HPP] Yoshua BengioAugust 11, 202521 min
33 connections·40 entities in this video→International AI Safety Report
- 💡 Yoshua Bengio chairs an International AI Safety Report, inspired by the IPCC, involving 30+ countries and 100 experts.
- 🎯 The report's goal is to provide an evidence-based synthesis of scientific findings on AI safety for policymakers, not to make recommendations.
- 📌 It highlights the potential for societal-scale harm within just a few years, urging policymakers to consider this possibility.
Accelerating AI Capabilities and Emerging Risks
- 📈 There is clear evidence of exponential progress in AI capabilities, with systems achieving
Knowledge graph40 entities · 33 connections
How they connect
An interactive map of every person, idea, and reference from this conversation. Hover to trace connections, click to explore.
Hover · drag to explore
40 entities
Chapters7 moments
Key Moments
Transcript77 segments
Full Transcript
Topics15 themes
What’s Discussed
International AI Safety ReportCatastrophic AI risksSuperintelligenceScientist AIAI agencyAI capabilitiesDeceptive AI behaviorSelf-preserving AI behaviorNon-agentic AIAI safety researchAI regulationInternational AI cooperationEvidence dilemma (AI policy)Large reasoning modelsGuardrails (AI safety)
Smart Objects40 · 33 links
Concepts· 22
People· 4
Medias· 2
Companies· 5
Products· 2
Locations· 2
Events· 3