Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
October 06, 2025
·
Seattle
AutoLearn: Deterministic Agents
The talk explains how to replace costly, error‑prone AI reasoning loops with deterministic code, reducing failure rates and improving performance in autonomous agents.
Video
Overview
AI agent reasoning loops are expensive and fail often (5%+). What if we could move those conditions off of the transformer and into deterministic code, automatically?
Links
Tech stack