Collection
Videos (403)
Browse all imported and processed videos.
Two Bugs That Hid in Plain Sight: A vLLM Debugging Detective Story — Asaf Gardin & Yuval Belfer
completed
18:06
RAG on
Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards — Filip Makraduli
completed
17:18
RAG on
Are LLM Performance Benchmarks Reliable? — Ashok Chandrasekar & Jason Kramberger, Google
completed
16:07
RAG on
Vertical Mobility: Inference from MVP to Trillion-Parameter Workloads — Sitanshu Gupta, CoreWeave
completed
15:22
RAG on
Operating Distributed Inference Systems at Scale — Nishant Gupta & Naman Ahuja, Meta
completed
19:50
RAG on
Routing LLM Inference in Production: From Engine Signals to Policy — Qianru Lao & Lu Zhang, OpenAI
completed
18:12
RAG on
The Search Engine for the Agentic Web — Will Bryk, Exa
completed
17:48
RAG on
Rebuilding the web for agents — Liad Yosef, MCP Apps
completed
20:40
RAG on
If we want them to do Knowledge Work, design them as Knowledge Agents — Benjamin Clavié, Mixedbread
completed
17:54
RAG on
Stop Chunking Like It's 2022 — Yuval Belfer, AI21 Labs
completed
18:00
RAG on
The End of TCP for AI Clusters — John Ousterhout, Stanford
completed
18:48
RAG on
Connect AI to Billions of Legal Documents — Simon Eskildsen, turbopuffer & Jacob Lauritzen, Legora
completed
20:36
RAG on
Your Agreements Are a Database You Can't Query — Hiral Shah, Docusign & Sean Sodha, NVIDIA
completed
18:21
RAG on
Realtime Voice Agents with Frontier Intelligence — Bohan Li, EliseAI
completed
13:13
RAG on
"My name is... my name is...": A Linguistic Map for Voice Agents — Midam Kim, ServiceNow
completed
15:04
RAG on
I Monitored Crime Audio. Voice Agents Scare Me More. — Sumanyu Sharma, Hamming AI
completed
16:04
RAG on
5 Voice Agent Failure Modes You'll Hit in Week One — Venky B, Plivo
completed
26:46
RAG on
We let an AI agent execute Bash and lived to talk about it — Sarah Sanders, PostHog
completed
21:00
RAG on
No Memory, No Harness: Why the Database Is the Last Line of Defense — Kay Malcolm, Oracle
completed
21:37
RAG on
Every step you take, every call you make: the reliable agent stack — Giselle van Dongen, Restate
completed
20:49
RAG on