Llm

SLUUG Talk: Demystifying Large Language Models on Linux

Talk for the St. Louis Unix Users Group about running and understanding Large Language Models on Linux.

I Tried to Voice-Clone Myself in 90 MB

A tiny LLM in the browser, mixed at sample time with a token-level n-gram trained on every word I have published. Result is mediocre. Architecture is interesting. Notes on what worked, what didn't, and what would make it work.

TD Learning for Exemplar Retrieval: Why It Doesn't Really Work

I tried closing the loop on retrieval-augmented generation with TD learning. A trivial baseline matched the full method. Here's the lesson.

Compression Enables Generalization: Wake-Sleep Cycles for Logic Programming with LLM Integration

Superintelligence May Not Require a Breakthrough

The most dramatic possibility in AI might arrive through the most mundane mechanism. Not a beam of sacred light. A sufficiently good build system.

A Map of My Open Source Ecosystem

A guided tour through my open-source ecosystem: encrypted search theory, statistical reliability, Unix-philosophy CLI tools, AI research, and speculative fiction. How the projects connect and where to start.

Value Functions Over Reasoning Traces

What if reasoning traces could learn their own usefulness? A simple RL framing for trace memory, and why one reward signal is enough.

From A* to GPT: Rational Agents and the Representation Problem

The classical AI curriculum teaches rational agents as utility maximizers. The progression from search to RL to LLMs is really about one thing: finding representations that make decision-making tractable.

Your Boring Stack Isn't Boring Enough

A response to the 'boring stack' discourse. Why CLI-first, standards-based development is even more boring (and more future-proof) than you think.

src2md: Fitting Codebases into LLM Context Windows

A tool that converts source code repositories into structured, context-window-optimized Markdown for LLMs, with intelligent summarization and importance scoring.

Networks of Thought: Finding Your Research Niche in the Age of LLMs

On research strategy, what complex networks reveal about how we think through AI conversations, and building infrastructure for the next generation of knowledge tools.

CTK: Conversation Toolkit

A plugin-based toolkit for managing AI conversations from multiple providers. Import, store, search, and export conversations in a unified tree format. Built for the Long Echo project.

DreamLog: Logic Programming That Dreams to Improve Itself

A logic programming system that alternates between wake and sleep phases, using LLMs for knowledge generation during wake and compression-based learning during sleep.

Language Calculus: An Algebraic Framework for LLM Composition

A mathematical framework that treats language models as algebraic objects with compositional structure.

KL-Threshold Routing Between LLMs: What Speculative Decoding Already Solved

In 2023 I drafted a paper on routing between a large and small LLM via KL-divergence thresholds. Speculative decoding had already solved the problem more rigorously. Here is the post-mortem.

MCTS-Reasoning: Tree Search for LLM Reasoning

Applying Monte Carlo Tree Search to large language model reasoning, with a formal specification of the algorithm.

Cluster-Aware Retrieval for RAG Systems

Using GMM clustering to improve retrieval in topically diverse knowledge bases

Latent Reasoning Traces: Memory as Learned Prior

What if LLMs could remember their own successful reasoning? A simple experiment in trace retrieval, and why 'latent' is the right word.

Neural Language Models: From RNNs to Transformers

The evolution of neural sequence prediction, and how it connects to classical methods

A Home Lab from Spare Parts

I built a home lab from spare parts and water-damaged hardware for local LLM experimentation. CPU-only inference is slow, but you learn things cloud APIs hide.

Discovering ChatGPT: Reconnecting with AI Research

Encountering ChatGPT during cancer treatment and recognizing the Solomonoff connection. Language models as compression, prediction as intelligence. A personal inflection point reconnecting with AI research after years in survival mode.