| AI Engineer Paris 2026 Main Stage: Google DeepMind, ElevenLabs, Hugging Face & Stripe | Day 2 | Sep 24, 2026 | 8:44:15 | 16.5K |
| I Gave an AI a Body — Cyrus Clarke, MIT Media Lab | Sep 24, 2026 | 20:48 | 1.2K |
| One Operator, Many Drones: Inside Skydio's Autonomy Stack — Suchet Bargoti, Skydio | Sep 24, 2026 | 20:48 | 1.2K |
| Robot Demos Are Easy. Reliability Is Hard — Jason Ma, Dyna Robotics | Sep 24, 2026 | 26:42 | 1.3K |
| Physical AI's Next Bottleneck Is Finding the Right Video — Rafael Levi, Bright Data | Sep 24, 2026 | 16:32 | 2K |
| World Models Need Causality, Not Pretty Pixels — Christopher Manning, Moonlake AI | Sep 24, 2026 | 51:36 | 1.9K |
| Robotics Has Been Stuck for 70 Years — Deepak Pathak, Skild AI | Sep 24, 2026 | 28:18 | 1.9K |
| AI Engineer Paris 2026 Opening Keynotes: Mistral, Langfuse & Sizzy | Day 1 | Sep 24, 2026 | 1:13:36 | 9.7K |
| From Scratch to SOTA: Training a 3B State-Space Vision Model — Krishna Prasad Srinivasan, Sarvam | Sep 23, 2026 | 21:09 | 7.6K |
| From VLM/VLA's to Embodied Agents — Armen Aghajanyan, Perceptron AI | Sep 23, 2026 | 20:42 | 3.6K |
| You’re Not Thinking Big Enough: Rebuilding Food Systems with AI Agents — Cody Menefee, Firecrawl | Sep 23, 2026 | 18:26 | 6.6K |
| The Best Models Still Reason Like Toddlers — Andrew Dai, Elorian | Sep 23, 2026 | 18:17 | 3.5K |
| From Ingestion to Agents: How AI Teams Build on Document Intelligence — Adit Abraham, Reducto | Sep 23, 2026 | 22:29 | 7.3K |
| Modality Misalignment and Originality Attribution in Short-Form Video — Aditya Gautam, Meta | Sep 23, 2026 | 21:32 | 2.8K |
| Skill issue: stop deploying vision language models, use them with Skills — Merve Noyan, Hugging Face | Sep 23, 2026 | 19:14 | 6.3K |
| Building the Document Context Layer for AI Agents — Jerry Liu, LlamaIndex | Sep 23, 2026 | 21:04 | 22.3K |
| The Dark Arts of Skill Engineering — Paul Bakaus, Renaissance Geek (Impeccable) | Sep 21, 2026 | 1:04:53 | 23.3K |
| Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards — Filip Makraduli | Sep 19, 2026 | 17:18 | 15.6K |
| Two Bugs That Hid in Plain Sight: A vLLM Debugging Detective Story — Asaf Gardin & Yuval Belfer | Sep 19, 2026 | 18:06 | 8.7K |
| The Frontier AI Inference Cloud for Agents — Byung-Gon (Gon) Chun, FriendliAI | Sep 19, 2026 | 14:59 | 16.3K |
| Large clusters for small models — Daniel Svonava, Superlinked | Sep 19, 2026 | 25:07 | 9.7K |
| What's New in Inference Engineering — Philip Kiely, Baseten | Sep 19, 2026 | 19:09 | 13K |
| Vertical Mobility: Inference from MVP to Trillion-Parameter Workloads — Sitanshu Gupta, CoreWeave | Sep 19, 2026 | 15:22 | 9.3K |
| Are LLM Performance Benchmarks Reliable? — Ashok Chandrasekar & Jason Kramberger, Google | Sep 19, 2026 | 16:07 | 6.1K |
| Routing LLM Inference in Production: From Engine Signals to Policy — Qianru Lao & Lu Zhang, OpenAI | Sep 19, 2026 | 18:12 | 7K |
| Operating Distributed Inference Systems at Scale — Nishant Gupta & Naman Ahuja, Meta | Sep 19, 2026 | 19:51 | 6.7K |
| Total Recall: Agent Memory and Harness Engineering — Ignacio Martinez, Oracle | Sep 18, 2026 | 1:00:47 | 27K |
| Homa: The End of TCP for AI Clusters — John Ousterhout, Stanford | Sep 17, 2026 | 18:48 | 166.6K |
| Stop Chunking Like It's 2022 — Yuval Belfer, AI21 Labs | Sep 16, 2026 | 18:01 | 28.7K |
| Where RL Will Take Search — Maximilian-David Rumpf, SID.ai | Sep 16, 2026 | 9:36 | 10.8K |
| Connect AI to Billions of Legal Documents — Simon Eskildsen, turbopuffer & Jacob Lauritzen, Legora | Sep 16, 2026 | 20:36 | 13K |
| Your Agreements Are a Database You Can't Query — Hiral Shah, Docusign & Sean Sodha, NVIDIA | Sep 16, 2026 | 18:22 | 6.3K |
| If we want them to do Knowledge Work, design them as Knowledge Agents — Benjamin Clavié, Mixedbread | Sep 16, 2026 | 17:55 | 29.3K |
| Rebuilding the web for agents — Liad Yosef, MCP Apps | Sep 16, 2026 | 20:41 | 7.6K |
| The Search Engine for the Agentic Web — Will Bryk, Exa | Sep 16, 2026 | 17:49 | 7.6K |
| The unreasonable effectiveness of BM25 for agentic search — Jo Kristian Bergum, Hornet.dev | Sep 16, 2026 | 18:29 | 57.6K |
| Pinecone 2.0 — Edo Liberty, Pinecone | Sep 16, 2026 | 19:50 | 7.5K |
| Act, Confirm, or Stop? Smarter behavior for AI assistants, wearables & robots — Amit Desai, Roku | Sep 15, 2026 | 20:25 | 6.7K |
| "My name is... my name is...": A Linguistic Map for Voice Agents — Midam Kim, ServiceNow | Sep 15, 2026 | 15:05 | 5.9K |
| Realtime Voice Agents with Frontier Intelligence — Bohan Li, EliseAI | Sep 15, 2026 | 13:14 | 6.6K |
| 5 Voice Agent Failure Modes You'll Hit in Week One — Venky B, Plivo | Sep 15, 2026 | 26:46 | 8.9K |
| 1 Trillion Phone Calls/yr, 10% Error rate: The Crisis in Voice AI — Sumanyu Sharma, Hamming AI | Sep 15, 2026 | 16:04 | 4.9K |
| Tolan: Voice-First AI Companion — Paula Dozsa, Tolan | Sep 15, 2026 | 15:08 | 5.6K |
| Your Voice Agent is Just a Walkie Talkie — Neil Zeghidour, Gradium | Sep 15, 2026 | 19:14 | 4.9K |
| Voice Agents Can Just Do Things — Charlie Guo, OpenAI | Sep 15, 2026 | 15:50 | 6.8K |
| Speech-to-Speech Model Research at Google DeepMind — Valeria Wu Fon & Tom Ouyang, Google DeepMind | Sep 15, 2026 | 16:42 | 4.7K |
| Agents Without Code: Skills, YAML, and Filesystems Replaced Python — Philipp Schmid, Google DeepMind | Sep 14, 2026 | 18:28 | 40.1K |
| How We Solved Agent Building — Andrew Qu, Vercel | Sep 14, 2026 | 17:34 | 129.9K |
| No Memory, No Harness: Why the Database Is the Last Line of Defense — Kay Malcolm, Oracle | Sep 14, 2026 | 21:37 | 8.2K |
| We let an AI agent execute Bash and lived to talk about it — Sarah Sanders, PostHog | Sep 14, 2026 | 21:00 | 6.9K |