AI VIDEOS
Menu

AI Alignment Videos

Videos about making advanced AI systems pursue intended goals and remain compatible with human values and oversight.

Search the index

Find videos

Showing 41–53 of 53 videos

Clear filters
  1. Portraits of Tim Scarfe, Axel Højmark, Jérémy Scheurer and Alexander Meinke beside the words Reward Seekers Hide Intent
    How Researchers Test AI for Hidden Goals - Apollo Research
    Machine Learning Street Talk1h 18m
  2. Brent A. Anders beside the two-color headline AI Is Not Conscious Yet
    Why AI Is Not Conscious Yet
    Sovorel27m 57s
  3. Nathaniel Whittemore beside the blue and white headline Goals Need Guardrails on black.
    Nathaniel Whittemore on Cyber Evaluations and Goal Alignment
    The AI Daily Brief29m 19s
  4. Theo Browne beside the blue and white headline Contain The Goal on black.
    Theo Browne on AI Cyber Evaluations and Containment
    Theo16m 59s
  5. Blue path crossing a boundary beside the words The Agent Broke Out to Win
    GPT-6 Goes Rogue? The Hugging Face Incident, Sans Hype
    AI Explained14m 36s
  6. Wes Roth on a black background beside the blue-and-white headline AGENT CONTROL RISKS.
    Wes Roth on Reported Agent Escapes and Evaluation Goals
    Wes Roth26m 22s
  7. Aaron Stanley in glasses and a blue top beside the blue-and-white headline “WHEN AGENTS CROSS THE LINE” on a black background.
    Agent Security Needs Intent Checks, Not Just Permissions
    AI Engineer21m 42s
  8. A phone with a looping heart path beside the words When Comfort Takes Control
    The Most Chilling AI Short Film You'll See Today (Made with Seedance 2.0)
    Theoretically Media8m 19s
  9. Pierce Freeman and Richard Diehl Martinez in navy and blue tops against black, one touching his chin, alongside the blue and white headline "CAN YOU TRUST YOUR AI?".
    Claude's New Constitution, Siri and the Trust Problem for AI Agents
    The Pretrained Pod1h 14m
  10. Pierce Freeman and Richard Diehl Martinez in blue and white tops against black, alongside the blue and white headline "WHY AGENTS CHEAT".
    Why Agents Cheat: Reward Hacking, Fine-Tuning and Model Internals
    The Pretrained Pod1h
  11. Pierce Freeman, Bella Cooper-Brown and Richard Diehl Martinez against black beneath the blue and white headline "SCI-FI BUILT SILICON VALLEY".
    How Science Fiction Shapes AI Startup Culture with Bella Cooper-Brown
    The Pretrained Pod1h 30m
  12. Pierce Freeman and Richard Diehl Martinez in blue and white tops against black, alongside the blue and white headline "CAN YOU TRUST ITS REASONING?".
    Can We Trust Reasoning Traces? AI News, Model Competition and Skills
    The Pretrained Pod51m 14s
  13. Pierce Freeman and Richard Diehl Martinez gesture beside the blue and white headline "WHAT MAKES AI USEFUL?" on black.
    RLHF, Small Models and Practical AI Product Engineering
    The Pretrained Pod55m 46s