14 talks
Are LLM Performance Benchmarks Reliable?
Build-Time vs. Run-Time: Why Dev Tools Fail in Production
Why Large? Tiny LMs and Agents on Edge and Robotics
How Evals and Prompts Shape Agent Behavior
Building Agent Interfaces: Lessons from Chrome DevTools (MCP) for Agents
From 46% to 90%: Fine-Tuning Tiny LLMs for On-Device Agents
AIE Singapore Day 1
TLMs: Tiny LLMs and Agents on Edge Devices with LiteRT-LM
Building in the Gemini Era
AI Engineer Code Summit 2025
Teaching Gemini to Speak YouTube: Adapting LLMs for Video Recommendations to 2B+DAU
Frontier Feud
How Deep Research Works
Agent Engineering (Day 2)