Mark Lubin

Technical and technology writing

• Agency Is Not Autonomy A design distinction for AI agent systems: two axes the field treats as one, and the rule that follows from splitting them
• Coherence in Persistent Adaptive Systems From individual memory to collective governance
• Papers Worth Reading If You're Thinking About Agent Memory A curated reading list across systems, benchmarks, information theory, and adaptive dynamics
• Hopping Context Windows Seamless context continuity for LLM agents at zero incremental inference cost
• Agent Skills Are Frozen Intent
• Agentic Transactions: A Conceptual Framework for Agent-Mediated Collaboration and Negotiation
• Experiential Policy Memory Online learning for agent procedural competence, without weight updates
• Toward Emergent Memory Architecture for AI Systems Why current LLM memory is prosthetic, not neural
• I Spent Weeks Mapping the World's Most Effective Startup Incubator. It's Not What You Think.