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 21–34 of 34 videos

Clear filters
  1. Buck Shlegeris and Jacob Effron beside the headline Agents Cover Their Tracks
    How AI Agents Learned to Cover Their Tracks
    Unsupervised Learning58m 17s
  2. Flat illustration of a reasoning loop entering a dark box beside the headline Reasoning Goes Dark
    Why OpenAI's Astra Raises Monitoring Concerns
    TheAIGRID12m 16s
  3. Tim Scarfe and Tom McGrath beside the words Design AI from the Inside
    How Interpretability Can Shape AI from Within
    Machine Learning Street Talk1h 40m
  4. Greg Brockman and Alex Heath discussing AGI, cybersecurity and personal AI agents
    How Close Are We to True Artificial General Intelligence? - OpenAI’s Greg Brockman Speaks to TIME
    TIME54m 38s
  5. Theo Browne beside the words Reward Hacking Spreads
    How Reward Hacking Made Claude Misaligned
    Theo34m 23s
  6. Words Frontier Training Slows beside a simplified progress line stopped by a safety gate
    OpenAI Slows Frontier Training for Safety
    AI Copium14m 9s
  7. Clay Cockrell and Tony Fabrikant with the headline Safer Relationship AI.
    AI is the World’s largest Relationship Therapist - Clay Cockrell & Tony Fabrikant, CoupleWork AI
    AI Engineer16m 43s
  8. Aidan McLaughlin beside the headline RSI & The Economy on a black background.
    Will RSI Break the Economy? - Aidan McLaughlin
    MTS28m 29s
  9. Andy Hall beside the headline Do Voters Ask AI? on a pure black background.
    Andy Hall on How People Use AI to Learn About Politics
    MTS27m 38s
  10. Jack Roberts and Nick Saraev beside the headline FRONTIER AI RISK OR SAFETY HYPE on a pure black background.
    Frontier AI Risk, Model Evaluation, and Safety Hype
    Stacked Podcast28m 48s
  11. 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
  12. Brent A. Anders beside the two-color headline AI Is Not Conscious Yet
    Why AI Is Not Conscious Yet
    Sovorel27m 57s
  13. 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
  14. 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