RoTSL

Bypassing the OS to Run LLMs: What I Learned Building a Firmware-Centric Runtime

I spent the last few months asking a question that sounds slightly unhinged: what happens if you strip the operating system out of the LLM…

NoB (Noticeably Better): a compiled language that tries to stay out of your way

Most new languages promise the same things: performance, simplicity, better tooling. NoB is trying to hit those too — but the interesting…

You don’t need 20 resumes. You need one that compiles.

Stop rewriting your resume for every job. Treat it like data instead.

SMGP [Spectral Memory Graph Processor] : Building an AI That Actually Remembers What You Told It

Persistent, verifiable AI reasoning with spectral graphs, TDA, HDC, graph rewriting, and FPGA acceleration.

I Built a Safety Net for Python Environments Because I Was Tired of Debugging “It Works on My…

Why every Python developer needs a preflight check for their code

The Ulysses Prediction Engine

What Happens When You Try to Reverse Biology? A Deep Look at the Protein → DNA Analysis Simulator

Most biology tools move in one direction. DNA becomes RNA. RNA becomes protein.

Hypercontext is for building AI agents that are aware of their own context.

Inspired by the Hyperagents paper's vision of meta-cognitive AI systems, Context Fission and Karpathy's auto-research

Your LLM prompts are probably wasting 90% of tokens. Here’s how I fixed mine.

I keep running into the same problem with LLM apps.

Health AI on Notion with Tribe V2

Local-first Notion health tracker with TRIBEv2 brain analysis, AI health insights, symptom logging, goals, medications, appointments, and a…

From Kidney Stones to Convergence

The strange path from ultrasound physics to rethinking how solvers move through space