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 1–20 of 44 videos

Clear filters
  1. The headline OpenAI Safety Pause above a blue shield surrounding a white AI chip on a black background.
    OpenAI Just Stopped ALL Training...
    AI Copium9m 53s
  2. Houda Nait El Barj and Theo Jaffee against a black background beside the blue and white headline “PERSONAL AGENTS / HUMAN LIMITS”.
    Personal Agents Will Unlock Cheap Drug Discovery - OpenAI
    MTS21m 3s
  3. Roman Yampolskiy, Nate Soares, Ed Zitron and Andrew McAfee beneath blue “AI RISK” and white “WHERE’S THE LINE?” on black.
    99% Chance of Extinction?! This AI Debate Got HEATED…
    AI Copium23m 22s
  4. Pierce Freeman, Richard Diehl Martinez and Jacob Coxon in white, blue and yellow tops beneath "AI RISK OR REGULATORY CAPTURE?" in blue and white on black.
    The Anthropic Quitter Tweet Was Suspiciously Well-Timed. Here's Why.
    The Pretrained Pod1h 1m
  5. Nathaniel Whittemore with Dario Amodei and Sam Altman against a black background framing the debate over pacing frontier AI.
    AI Companies Begin to Align Around Slowdown
    The AI Daily Brief33m 27s1 VIEW
  6. Nick Saraev in a light attention-blue top and Jack Roberts in an off-white top on a black background beside the headline “CAN GROK WIN?”.
    Grok 4.8: Can It Win the AI War?
    Stacked Podcast30m 23s
  7. Brendan Rappazzo in a plain blue T-shirt beside the headline Stress Test Your Morals on a pure black background.
    Adversarial AI Agents That Stress-Test Moral Rules
    AI Engineer16m 59s
  8. Sam Altman with Alyson Shontell beside the headline AI CONTROL SAFETY AND PAUSING on a pure black background.
    Sam Altman on AI Control, Safety, and the Case for Pausing
    Fortune Magazine46m 6s
  9. A flat attention-blue alert symbol on a black background beside the headline ‘AI SAFETY VS PROGRESS’.
    The People Building AI Are Scared…
    AI Copium18m 27s
  10. Nathaniel Whittemore in a dark-blue shirt and Evan Hubinger in an attention-blue shirt on a black background beside the headline ‘A 10% AI EXTINCTION RISK?’.
    Anthropic Researcher Says 10% Chance AI Kills All Humans
    The AI Daily Brief31m 58s1 VIEW
  11. Matthew Berman in an attention-blue shirt on a black background beside the headline ‘AI PROGRESS IS ACCELERATING’.
    We need to talk about this...
    Matthew Berman32m 54s
  12. Rob Miles beside the words Can We Read AI Reasoning?
    Neuralese and the Limits of Chain-of-Thought Monitoring
    Computerphile27m 17s
  13. Pierce Freeman in off-white gestures beside Richard Diehl Martinez in blue touching his chin, against black beneath the blue and white headline 'SAFER, BUT HARDER TO READ?'.
    What OpenAI Won't Tell You About GPT-6 Astra
    The Pretrained Pod1h 19m
  14. Károly Zsolnai-Fehér beside the headline Did AI Solve It? on a pure black background.
    Did AI Solve the Navier-Stokes Millennium Problem?
    Two Minute Papers9m 17s2 VIEWS
  15. Theo Browne on a black background beside the headline ‘AI SAFETY RACE’.
    Anthropic employees are quitting due to safety concerns
    Theo26m 33s
  16. Jack Roberts in attention blue, Evan Hubinger in off-white and Nick Saraev in dark navy above the blue and off-white headline AI Risk Goes Public on black. Evan has a natural fair pink complexion.
    Anthropic's Alignment Lead Says AI Might Kill Us All
    Stacked Podcast26m 35s
  17. Jakub Pachocki against a black background beside the headline “AI RESEARCH OUTPACES CONTROL”.
    OpenAI’s Chief Scientist Just Issued a Terrifying Warning…
    AI Copium16m 31s
  18. Daniel Kokotajlo, Thomas Larsen and Tim Scarfe discussing specialized AI collectives and safeguards for advanced AI.
    How Many Narrow AIs Could Behave Like One Superintelligence - Daniel Kokotajlo and Thomas Larsen
    Machine Learning Street Talk1h 29m
  19. Thomas Larsen and Daniel Kokotajlo beside the headline Is Astra Harder to Monitor? on a black background.
    OpenAI's Astra Model Is Less Monitorable - Thomas Larsen & Daniel Kokotajlo
    MTS32m1 VIEW
  20. Two men in blue T-shirts flank the white and blue question WHO CONTROLS AI? on a black background.
    Wes Roth on AI Goals, Values and Human Control
    Wes Roth29m 27s