Why AI Agents Forget by Design
An honest technical explanation of why current AI agents have no persistent memory, what that costs in production, and what better agent memory architectures would actually need to solve.
Stan Tyan
Writing
An honest technical explanation of why current AI agents have no persistent memory, what that costs in production, and what better agent memory architectures would actually need to solve.
How subscription metrics - ARR, ARPPU, retention, LTV, CAC, and unit economics - connect into one system, with formulas, worked examples, and the decisions each metric informs.
A practitioner's guide to the 10 machine learning algorithms that handle the majority of real-world tabular, text, and classification problems, with decision criteria and production tradeoffs.
Projects
A project using APIs, spreadsheet transformation, and Tableau to turn personal trip data into an ongoing dashboard.
A continuation of the underwater monitoring research, focused on distributed sensing, mobile underwater vehicles, and protocol choices suited to constrained environments.
A research-oriented project about underwater sensing, acoustic communication constraints, and a protocol stack tailored to river monitoring.