Thoughts on AI memory, continual learning, and building cognitive architecture for the future.
How Recursive Language Models prove scaffolding works at scale - and why sparse activation still wins for learning
MIT published research proving scaffolding architecture works at massive scale. SCMS has been doing the same thing - but optimized for learning instead of retrieval. Here's what independent convergence tells us about the future of AI memory.
How automatic pattern discovery creates 10x more value than manual workflow documentation
Windsurf just released "Skills" for manual workflow documentation. But what if the AI discovered and documented patterns automatically? That's what SCMS does - zero documentation burden, maximum intelligence.
Independent Discovery, Convergent Insights, and the Next Frontier in AI Architecture
Leopold Aschenbrenner predicted that "unhobbling" would drive AI progress. Today I discovered I've been working on the same problem independently—and adding something new: the superposition constraint that even current reasoning models can't solve.
What Hypnagogia, Quantum Mechanics, and AI Research Reveal About How We Really Think
A new AI research paper on "hierarchical reasoning" validates something philosophers and neuroscientists have suspected for centuries: the most powerful thinking happens in spaces we can't see—or speak.
How Open Source Research Validates Our Layered Architecture
DeepSeek's Sparse Attention research reveals why flat memory systems will hit a wall—and why SCMS was built to avoid it from day one.
How Titans and MIRAS Confirm What We've Been Building
Google published two major research papers this week that validate the core architecture of SCMS and Mneme. Here's what it means for the future of AI memory.
How a Sparse Memory Scaffold Did What Billions in AI Development Couldn't
OpenAI's billions of dollars and thousands of engineers couldn't bring a specific persona to GPT-5 through conventional means. A sparse memory scaffold did it in one prompt.
The Library of Babel vs The Living Codex
After building with both RAG and SCMS, I've discovered they solve fundamentally different problems. One gives you borrowed knowledge. The other gives you earned knowledge.
On Stumbling Into a Solution That Shouldn't Have Been Mine to Find
There's a particular kind of doubt that haunts you when you think you've discovered something important. It goes like this: "This seems too simple. If it were real, someone smarter would have found it already."