Intro to AI Safety, Remastered
Robert Miles AI Safety
Why leaders watch it
Plain-language grounding in AI alignment and risk for leaders who oversee AI programs.
Robert Miles gives a remastered introduction to AI safety adapted from a London talk. It lays out why advanced AI systems may pursue goals misaligned with human intent.
Takeaways
- Specifying goals precisely is hard
- Capable systems can behave in unintended ways
- Safety needs attention before scale
Topics: AI ethics, risk & governance
Related
- Leadership, Culture, and Ethics in Cybersecurity · Dr. Mansur Hasib - #DrCybersecurity
- Days to Seconds: Harnessing Confidential AI Agents with Kellie Romack · Opaque Systems, Inc.
- EU AI Act Explained: Everything You Must Know · Deloitte Nederland
- AI Governance for Board Members: Overseeing Risk, Talent, and Strategy · Center for Digital Transformation | CDT
- Speech at the UN Security Council on Frontier AI Risks & Global Governance · Yoshua Bengio
- Kellie Romack on ServiceNow's $355M AI Transformation | From 4 Days to 8 Seconds · CAIO AI Leadership Podcast
- OpenAI's GPT-4 Discussion with Red Teamer Nathan Labenz and Erik Torenberg · Cognitive Revolution "How AI Changes Everything"
- Kellie Romack on how ServiceNow Generated $355M in AI Value | Technovation 1062 · Metis Strategy
- Teddy Talks - Citizenship in a Republic (includes The Man in the Arena) · MedoraND
- Coexisting with AI: Can We Get It Right? A Talk by Stuart Russell · Yardi ScAI
- How Agentic AI Changes The Workplace — With Jacqui Canney and Kellie Romack · Alex Kantrowitz
- Resilience is a Choice | Jeff Harmon | TEDxHarvard Square · TEDx Talks