Mark Lubin
Writing
Synix
GitHub
Contact
Posts
Redbridge
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
Latent Dating
On loneliness, being half-seen, and matching on what you've lived
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