October 12 – 14, 2026 · Yerba Buena Center for the Arts, San Francisco, California
1–4 of 4 sessions
Evals are the highest-leverage infrastructure an AI team can own, and the tooling matters far less than the muscle. In this hands-on session we build an eval harness from an empty directory: golden sets, graders (exact, rubric, and LLM-judg…
Eli Rosenberg
Evaluation Engineer · Proofpoint AI
The most reliable AI app is the one that keeps working in airplane mode. Local-first AI stopped being a curiosity when small models crossed the "good enough" line for summarization, classification, and retrieval over personal data — all wor…
Kenji Sato
On-device ML Engineer · Pocket Models
Every platform team eventually faces the question: build the AI platform layer or buy it. Both answers are expensive and one of them is wrong for you specifically. This panel stages the argument properly, with a platform lead who built and…
Fatima Zahra
Head of Platform · Atlas Commerce
Layla Hassan
VP of Engineering · Harbor Finance
The transformer has been the answer for eight years, which historically is when architectures stop being the answer. This talk surveys the challengers honestly: state-space models, hybrid attention schemes, and the sparse and recurrent revi…
Elena Petrova
Research Engineering Director · Gradient Commons