All collections

AI Engineer World's Fair 2026

Talks from AI Engineer World's Fair 2026, drafted from the AI Engineer channel's own playlists. Editorial metadata is best-effort parsed and under review.

532 videos · refreshed 15 hours ago

Event 1
Track 1
Topic 5
  1. 326 —

    Brains vs Hands: How to Run AI Agents Safely in Production — Viren Baraiya Watched

    5K views 15 likes 1 comments

  2. 327 —

    Is Speculative Decoding Worth It? Profiling vLLM on NVIDIA Blackwell — Akamai Watched

    4.9K views 20 likes 5 comments

  3. 328 —

    How to avoid disaster when vibe-coding a billing engine — Andrew Garvin, Stripe Watched

    4.9K views 31 likes 1 comments

  4. 329 —

    Containment Is Lying to You: Measuring AI Agents Like Employees — Druid AI Watched

    4.9K views 9 likes 2 comments

  5. 330 —

    Why Your AI Agent Needs a Wallet: USDC and Nanopayments — Harshal Bhangale, Circle Watched

    4.8K views 26 likes 2 comments

  6. 331 —

    From VLM/VLA's to Embodied Agents — Armen Aghajanyan, Perceptron AI Watched

    4.8K views 17 likes 2 comments

  7. 332 —

    Your Agent Just Authorized What?! — Jay Mok & Ben Coumes, Paypal Watched

    4.8K views 11 likes 2 comments

  8. 333 ↑3

    The Desktop Frontier — Ahmad Osman, Osmantic Watched

    4.8K views 92 likes 6 comments

  9. 334 —

    How I Learned to Stop Worrying and Love the Sandbox — Matt Brockman, E2B Watched

    4.8K views 20 likes 0 comments

  10. 335 ↓2

    Teaching agents to pay — Anna Spysz, Stripe Watched

    4.8K views 31 likes 4 comments

  11. 336 ↓1

    Multimodal Collaborative Agents for Next-Gen Commerce — Nidhi Kaushik Vyas, Google DeepMind Watched

    4.8K views 24 likes 1 comments

  12. 337 —

    Why 80% Reliability Isn't Good Enough — Felipe Blanes, Amazon AGI Lab Watched

    4.8K views 15 likes 2 comments

  13. 338 —

    The Best Models Still Reason Like Toddlers — Andrew Dai, Elorian Watched

    4.7K views 35 likes 2 comments

  14. 339 —

    Frontier results, on device - RL Nabors, Arize Watched

    4.7K views 116 likes 6 comments

  15. 340 ↑1

    Your AI Agent Has No Nervous System — Matt Gibiec, Dynatrace Watched

    4.7K views 14 likes 0 comments

  16. 341 ↓1

    Loophole: Adversarial Agents To Stress Test Your Morality — Brendan Rappazzo, Morgan Stanley Watched

    4.7K views 18 likes 4 comments

  17. 342 —

    Deterministic Infra for Non-Deterministic AI Agents - Nishant Gupta, Meta Superintelligence Labs Watched

    4.6K views 88 likes 11 comments

  18. 343 —

    From Agent Traces to Agent Simulations — Rustem Feyzkhanov, Snorkel AI Watched

    4.6K views 76 likes 2 comments

  19. 344 —

    Agents Building Agents - Alfonso Graziano, Nearform Watched

    4.6K views 130 likes 4 comments

  20. 345 —

    How a Remote Company Builds AI Fluency — Em Shreve, Automattic Watched

    4.6K views 14 likes 1 comments

  21. 346 —

    Building Agents Is Trivial Now, Context Is the Next Frontier — Jeff Ng, Unblocked Watched

    4.6K views 72 likes 8 comments

  22. 347 ↑1

    Agentic Security: Permissions, Provenance, and the Agent Supply Chain — Steve Yegge, Gas Town Watched

    4.6K views 68 likes 7 comments

  23. 348 ↑4

    SimulationMaxxing: How we ship agents 20× faster — Aman Gupta (Nubank) + Shreya Rajpal (Snowglobe) Watched

    4.6K views 108 likes 3 comments

  24. 349 ↓2

    Build AI Systems for Discernment, Not Approval - Angel Ortmann Lee, Duolingo Watched

    4.5K views 133 likes 4 comments

  25. 350 ↓1

    AI Security Engineer Foundations + Certificate — Micah Silverman, Snyk Watched

    4.5K views 21 likes 0 comments