Aug 17, 2026

Context Engineering in 2026 — Louis-François Bouchard, Omar Solano & Samridhi Vaid, Towards AI

Experiments with an AI tutor reveal that not compacting context often outperforms summarization, leading to better recall, lower cost, and faster responses, primarily due to LLM API prompt caching. Compaction invalidates the cache, making it unexpectedly expensive. While cloud environments benefit from full history, local hardware limits necessitate compaction, highlighting the need to prioritize actual constraints over default compaction strategies.

Sep 25, 2025

No Priors Ep. 133 | With Alpha School Principal Joe Liemandt

Joe Liemandt, founder of Trilogy and principal of Alpha School, presents a radical vision for K-12 education powered by AI. He advocates for a "Time Back" model where students complete their core academics in just two hours a day using AI tutors, freeing the rest of their time for passion-driven workshops that build real-world life skills. This approach is built on principles of learning science, mastery-based progression, and a controversial but effective system of incentives.