Wax On, Weights Off: Knowledge Distillation Explained
What it is, how it works, why it saves money, and why it is rapidly reframing the US-China AI race
Encyclopedia Autonomica
Trusted by readers at Nasdaq, Nvidia, and Stanford, Encyclopedia Autonomica is the go-to guide for anyone building or deploying autonomous agents. We cover what matters: how real-life AI agents reason, plan, remember, and act.
Live Last read · last published · next check
Latest posts
A Self-Improving Code World Model Agent: From Orbit Wars to Capital Markets
Fighting digital wars in virtual orbits with knowledge transfer into capital markets.
DeepMind's (Code) World Models
When Letting LLMs Write the Simulator Matters More Than Letting Them Play
Agentic AI FinOps Playbook
A guide to tokenmaxxing AI costs in your organization
Recursive Language Models and Neurosymbolic Context Management
Recursive AI & neurosymbolic memory: how RLMs and symbolic architectures solve long-context reasoning for production AI agents.
Meta's Hyperagents & Self-Correcting Agents
A feedback loop that closes on the system's own implementation, not just its outputs. Five levels of self-correction. META, reinforcement learning, Q-learning
Tokenmaxxing and Optimizing Context with Deep Context Query
How intent-based filtering and RegEx-driven context extraction deliver 40–70% token reduction and better answers in agent systems.
Autonomous Agents in Space Logistics and In-Space Manufacturing
I haven’t written about space for too long a time.
The Absurd Effectiveness of Skills.md
this essay explores how we truly learn, by doing, and why that insight matters for the future of AI and knowledge work. As the shift from search engines to answer engines accelerates, a new paradigm emerges: cowork engines powered by “skills.” These structured, procedural workflows transform AI from passive responder to active collaborator. Using real-world examples like evolving developer tools,…
Pair-programming Superbill with Codex-5.2 and Claude Sonnet 4.6
The Value of Software Development Is (near) Zero