2026
-
The Lego work method: simplicity is an operating discipline
TLDR: The useful lesson from Lego is not a slogan about creativity. It is an operating discipline: stay close to the customer, keep accountability internal, reduce complexity, and make execution visible.
-
The Mythical Man-Month: chapters 1-6
The first six chapters still matter in the agent-coding era because Brooks was not mainly warning about typing speed. He was warning about coordination, conceptual integrity, integration, and the cost of turning programs into systems.
-
The Mythical Man-Month, Chapters 7-12: coordination is the product
TLDR: Chapters 7-12 make one old lesson feel new again: large software fails when coordination, budgets, documents, prototypes, and tools are treated as secondary work. Agent systems inherit the same constraints.
-
Graph of Agents: multi-agent value comes from information flow
TLDR: Graph of Agents is useful because it treats collaboration as a test-time graph problem: choose relevant agents, score their answers, pass messages in the right direction, and pool the result.
-
Paper reading skills: read for the argument, not the inventory
TLDR: A good paper-reading prompt should force the reader to recover the argument: problem, insight, method, evidence, and weakness. It should not reward section-by-section summarization.
-
SkillOpt: training the procedure outside the weights
TLDR: SkillOpt treats an agent skill as an optimizable text artifact. The model stays frozen, rollouts provide evidence, an optimizer proposes edits, and a validation gate accepts only real improvements.
-
The End of Software Engineering: code is becoming a runtime artifact
TLDR: The title is deliberately provocative, but the useful claim is narrower: agentic systems move durable value away from static code alone and toward intent, tools, memory, evals, observability, and governance.
-
LeanMarathon: long-horizon formalization as agent engineering
LeanMarathon turns paper-level Lean formalization into a recoverable multi-agent engineering system: blueprint, proof DAG, scoped workers, reviewer issues, and CI gates keep long tasks from drifting.