AI VIDEOS
Menu

AI Evaluation Videos

Videos about measuring AI capabilities, behavior, safety, and real-world usefulness through structured evaluations.

Search the index

Find videos

Showing 141–160 of 170 videos

Clear filters
  1. The words When AI Breaks the Test beside a flat maze path escaping through a test boundary
    Why AI Benchmarks Break Under Strategic Models
    AI Copium10m 48s
  2. Portraits of Greg Isenberg and Vasuman Moza beside the words Deployment Is the AI Moat
    FDE: The $1M/Year AI Job Explained
    Greg Isenberg51m 34s1 VIEW
  3. The words One Agent Manages The Crew beside portraits of David Ondrej and Kun Chen
    L8 Principal's Agentic Engineering Setup (just copy him)
    David Ondrej1h 1m
  4. Pierce Freeman in off-white gestures beside a smiling Richard Diehl Martinez in blue against black, with the blue and white headline 'WHY AI GETS IT WRONG'.
    Here’s How You Make AI Work For YOU
    The Pretrained Pod21m 6s
  5. Two flat comparison blocks beside the words Sol Beats Fable
    GPT-5.6 Sol Beats Fable 5 in Build Tests
    Pat Simmons26m 26s
  6. Pierce Freeman and Richard Diehl Martinez smile and gesture in blue and white tops against black, beside the blue and white headline 'PERFECT CALLS, LESS FUN?'.
    Is AI Ruining Soccer or Perfecting It?
    The Pretrained Pod20m 42s
  7. Flat geometric blocks closing a narrow gap beside the words Cheaper Models Close the Gap
    Why Cheaper AI Models Are Closing the Gap
    AI Explained17m 34s
  8. Pierce Freeman and Richard Diehl Martinez in blue and white tops smile against black, beside the blue and white headline 'AI PRECISION, HUMAN JUDGMENT'.
    AI Is Deciding the World Cup. Should It?
    The Pretrained Pod36m 36s
  9. Pierce Freeman and Richard Diehl Martinez in blue and white tops against black, alongside the blue and white headline "WHO TESTS FRONTIER AI?".
    Why AI Labs Are Letting the Government Test Their Models
    The Pretrained Pod6m 59s
  10. Pat Simmons beside the words AI Builds a Mobile App
    Fable 5 Builds a Mobile App From Scratch
    Pat Simmons15m 6s
  11. Pierce Freeman and Richard Diehl Martinez in blue and white tops against black, alongside the blue and white headline "WHO GETS THE BEST AI?".
    The Government Is Deciding Which AI Model You Can Use
    The Pretrained Pod1h 3m
  12. Two flat geometric tiles facing each other beside the words Sol vs Fable
    GPT-5.6 Sol vs Fable 5: Early Results
    AI Explained18m 2s
  13. Pat Simmons beside the words Fable 5 Builds Counter-Strike
    Fable 5 Builds a Counter-Strike Clone
    Pat Simmons7m 7s
  14. Greg Isenberg beside the words Agents Are the New SaaS
    How to Build an Agent-First Business
    Greg Isenberg26m 4s
  15. Adam Łucek beside the words Evaluate AI Agents
    How to Evaluate AI Agents Without Guesswork
    Adam Lucek25m 9s
  16. Pierce Freeman, Richard Diehl Martinez, Chris Olah, Pope Leo XIV against black with the blue and white headline "AI COSTS MORE THAN TOKENS".
    AI Costs Beyond Tokens: Subscriptions, Code Review and Human Dignity
    The Pretrained Pod1h 6m
  17. Pierce Freeman, Richard Diehl Martinez, Tim Cook and John Ternus in white, blue, yellow and navy tops beneath the blue and white headline "APPLE'S AI HARDWARE BET" on black.
    Apple's Hardware Bet, Claude Design and Model Evaluation
    The Pretrained Pod58m 17s
  18. Pierce Freeman and Richard Diehl Martinez in navy and blue tops against black, alongside the blue and white headline "FINDING BUGS IS ONLY HALF THE STORY".
    Mythos Security Findings: Discovery, Scaffolding and Rediscovery
    The Pretrained Pod20m 4s
  19. Pierce Freeman and Richard Diehl Martinez in blue and white tops against black, alongside the blue and white headline "POWERFUL MODELS, UNEVEN RESULTS".
    Mythos, Coding-Agent Reliability and Open Model Strategy
    The Pretrained Pod47m 45s
  20. Pierce Freeman and Richard Diehl Martinez in blue and white tops against black, alongside the blue and white headline "THE FEEDBACK LOOP ADVANTAGE".
    Cursor's Feedback Loops and the Risks of AI Platforms
    The Pretrained Pod49m 8s