Packed room at AIE Code Summit for Zach Lloyd on evals and self-improving agent loops
vikvang1 · x · 2026-11-13
Zach Lloyd drew a packed room at the AIE Code Summit in San Francisco, speaking on evals, benchmarks, A/B tests, and self-improvement loops for optimizing a "software factory" agent setup.
More from coding & agent
- Fable 5.2 ports a 28k-line path tracer to WebGPU by writing a custom compiler — edwinarbus · 2026-11-13
- Vercel launches UI SDK: reusable interface behavior primitives built for agents — shadcn · 2026-11-13
- Dev builds fully code-animated robotic biped in Unreal 5.8 with Fable 5.2 in 2 days — iamrobotbear · 2026-11-13
- Databricks Genie Agents add unstructured data analysis and GA native MCP connectors — matei_zaharia · 2026-11-13
- Code4Scene benchmark tests whether coding agents can actually reason about 3D space — Lianhuiq · 2026-11-13
- Demo: Atlas + Fable 5.2 + three.js for 3D Scene Generation — XRarchitect · 2026-11-13