The talk archive.

Training Taste — Thais Castello Branco, Taste Labs

Thais Castello Branco

YOLO Mode, Safely: MicroVM Sandboxes for Any Agent — Rowan Christmas, Docker

Rowan Christmas

Safety and governance · Coding agents · Coding harness

Keyword Search Is Dying. Is Your Catalog Ready for AI Agents? — PayPal

Nixon Dinh

Agentic commerce · Agentic search · Search intent and contextual meaning

Agent Memory Is Solved. Agent Learning Isn't. — Karthik Ranganathan, Yugabyte

Karthik Ranganathan · Heather Downing

Agent engineering · Information and coordination · Knowledge curation

Routing LLM Inference in Production: From Engine Signals to Policy — Qianru Lao & Lu Zhang, OpenAI

Qianru Lao · Lu Zhang

How AI Agents Pay: Checkout in ChatGPT and Google AI Mode — Sam Parsons, PayPal

Sam Parsons

Finance · APIs, MCP, and protocols · MCP Apps

AI Agents Are Just Distributed Systems Now — Salman Munaf, TikTok

Salman Munaf

World Models Need Causality, Not Pretty Pixels — Christopher Manning, Moonlake AI

Christopher Manning

What's New in Inference Engineering — Philip Kiely, Baseten

Philip Kiely

Where RL Will Take Search — Maximilian-David Rumpf, SID.ai

Maximilian-David Rumpf

RAG, context, and search · Reinforcement learning for retrieval · SID-1

Modality Misalignment and Originality Attribution in Short-Form Video — Aditya Gautam, Meta

Aditya Gautam

5 Voice Agent Failure Modes You'll Hit in Week One — Venky B, Plivo

Venky B

Z.ai GLM-4.6: What We Learned From 100 Million Open Source Downloads — Yuxuan Zhang, Z.ai

Yuxuan Zhang

Coding and developer tools · Evals · Infrastructure and deployment