These sources turn on feedback. They cover agent loops, queues, competing programs and an essay on attention. Ask of each one what signal closes the loop.
Digital Red Queen: Adversarial Program Evolution in Core War with LLMs
A research blog post on evolving competing programs in Core War with language models.
Harness Engineering for Self-Improvement
A long survey of research on agent harnesses that improve themselves.
Structural Backpressure Beats Smarter Agents
A blog post arguing that machine-checked gates in coding loops matter more than smarter models.
The Coming Loop
A blog post on harness-level loops around coding agents and the unease they cause.
Viable Systems: How To Build a Fully Autonomous Agent
A blog post applying Stafford Beer's Viable System Model to building autonomous AI agents.
Reinforcement learning, explained with a minimum of math and jargon
A plain-language newsletter article on how reinforcement learning helped make agentic AI models possible.
Waiting time, load factor, and queueing theory: why you need to cut your systems a bit of slack
A blog post explaining why waiting time climbs sharply as a system gets busier.
Almost anything you give sustained attention to will begin to loop on itself and bloom
An essay arguing that sustained attention makes experiences feed back on themselves and deepen.