AAIF Live

The Modern Software Engineer

How We Cut LLM Latency 70% With TensorRT in Production

AI Agents Summit Seattle

Ship Agents A Virtual Conference Track 2

Production Sub-agents for LLM Post Training

Fixing GPU Starvation in Large-Scale Distributed Training

MCP Dev Summit [Day 2] ft AWS, Docker, & Datadog

The Coding Agent Multiverse of Madness

How to Fix Your Agent's Amnesia: Lessons from Building a Self-learning Agent

Beyond SWE-Bench Pro - Where do Agents go from Here?

Practical Security for AI-generated Code

MCP Dev Summit [Day 1] ft. Anthropic, Hugging Face, Open AI & Microsoft

Choosing the Right Model is Hard. Maintaining Accuracy is Harder.

Stop Shipping on Vibes — How to Build Real Evals for Coding Agents

2026 The Year of Agent Orchestration

How to Make a Coding Agent a General Purpose Agent - Harrison Chase

Decomposing the Agent Orchestration System: Lessons Learned

Lessons from 25 Trillion Tokens — Scaling AI-Assisted Development at Kilo

Everything We Got Wrong About Research-Plan-Implement - Dexter Horthy

Dexter Horthy discusses the evolution and lessons learned from using coding agents, particularly the Research Plan Implement (RPI) methodology. He admits initial mistakes, such as not emphasizing code reading and over-relying on lengthy plan files. Horthy introduces CRISPI, a refined approach involving distinct stages ...

Performance Optimization and Software/Hardware Co-design across PyTorch, CUDA, and NVIDIA GPUs