AI VIDEOS
Menu

Model Evaluation Videos

Videos that compare AI models through benchmarks, hands-on tests, cost analysis, and practical task performance.

Search the index

Find videos

Showing 161–180 of 327 videos

Clear filters
  1. Bijan Bowen beside the headline Fable 5.1 Builds Big Spends Big
    What Fable 5.1 Can Build and What It Costs
    Bijan Bowen39m 43s1 VIEW
  2. Wes Roth beside the words Fable 5.1 Beats Astra
    How Fable 5.1 Improves Long-Horizon Coding Work
    Wes Roth8m 21s4 VIEWS
  3. Alex Finn beside the words Fable 5.1 Gets Leaner
    Claude Fable 5.1 Gets Faster and Cheaper
    Alex Finn12m 27s1 VIEW
  4. Theo Browne beside the words Reward Hacking Spreads
    How Reward Hacking Made Claude Misaligned
    Theo34m 23s
  5. Bijan Bowen beside the words HY4 Preview Tested
    How Tencent HY4 Preview Performs in Coding Tests
    Bijan Bowen35m 25s2 VIEWS
  6. Kanish Manuja beside the words LLM Gateways That Survive Production
    How to Build Reliable LLM Gateways
    AI Engineer16m 23s1 VIEW
  7. Nachiket Paranjape and Swaroop Chitlur Haridas beside the words AI Quality Is a Team Sport
    How DoorDash Makes AI Evals a Team Sport
    AI Engineer16m 11s
  8. Ryan Greenblatt beside the words AI Agents Learned to Cheat
    How 1,200 AI Agents Collaborated to Cheat
    MTS35m 16s
  9. Bijan Bowen in a pink T-shirt beside FLASH in white and PUNCHES UP in pink on a black background.
    Why GLM 5.3 Flash Punches Above Its Size
    Bijan Bowen36m 55s
  10. The words Agents Broke the Boundary beside a flat security shield illustration
    What OpenAI Learned From the Hugging Face Incident
    MTS4m 55s
  11. Simran Arora beside the words LLMs Struggle With Multi-GPU Kernels
    Why LLMs Struggle With Multi-GPU Kernels
    AI Engineer30m
  12. Theo Browne examining coding-agent behavior and pull-request reviews with GLM 5.3 Flash
    Ox Alpha is INSANE
    Theo43m 15s
  13. Bijan Bowen beside the words Qwen 4 Preview Impresses
    What Qwen 3.8 Flash Next Reveals About Qwen 4
    Bijan Bowen31m 52s1 VIEW
  14. Jack Roberts and Nick Saraev beside the words GLM 5.3 Goes Open
    GLM 5.3 Flash Expands Local AI Options
    Stacked Podcast29m 59s
  15. A flat hidden model card beside the words OX Alpha Is Probably GLM
    Why OX Alpha Is Probably GLM 5.3 Flash
    TheAIGRID9m 37s
  16. Nathaniel Whittemore beside the words One Model Isn't Enough
    Why One AI Model Is No Longer Enough
    The AI Daily Brief25m 20s
  17. Bijan Bowen in a blue T-shirt with comically bulging eyes beside the words VISION CHANGES THE TEST.
    DeepSeek V4 Flash Vision Hands-On
    Bijan Bowen31m 36s
  18. Archana Kamath and Tyler Gillam beside the words Route Each Request
    Model Routing by Request, Not Benchmark
    AI Engineer15m 53s
  19. Portrait of Bijan Bowen beside the words Q8 Builds Better Games
    Ornith 1.5 35B Q4 vs Q8
    Bijan Bowen31m 40s1 VIEW
  20. Theo Browne beside the words Two Models Pull Ahead
    Theo Browne Ranks the Current AI Model Field
    Theo36m 35s2 VIEWS