Writing Hub
AI governance essays, reasoning systems notes, experiment logs, and technical writing across BioAI and engineering practice.
Project Topics
Now Is the “Early, Messy Renaissance” of AI — Reading 2025 from a Florentine Workshop
Is AI a bubble or a renaissance? A practical playbook for founders and AI teams to move beyond hype with metrics, reproducibility, and real results.
Everyone’s Racing in the AI Era — Speed as Fever, Craft as Cure
In the AI era, speed is a fever and craft is the cure. A true story of wielding the 'fire-axe' of speed, a costly crash, and the 'stitches' (rituals & a 7-day plan) I used to mend the raft.
Pretty, but Wrong — How I Stop AI from Shipping Beautiful Garbage
AI can generate clean-looking code fast—but without discipline it becomes “beautiful garbage” that silently rots your codebase. Learn six rules to prevent it.
The Paper That Runs Itself: Why AI-Era Research Must Be Code-Native
Literate Programming, DevOps for Research, Research Infrastructure, Continuous Integration, AI Transparency, Scientific Publishing, arXiv Culture
Black Mirror: Plaything — Could a QR Code Really Hack the World?
Black Mirror imagines a QR-code apocalypse. As a Flame Glyph developer, I unpack what’s plausible today — local device disruption — and what remains fiction.
Why I Don’t Want to Be an AI Plumber (Like Super Mario)
I quit AI automation after a week. Not out of laziness, but to ask a bigger question: Is AI just a tool for efficiency, or a partner in creation?
I Built 2 Failed SaaS Products. Here’s What They Taught Me About Value in the Age of AI
After two failed SaaS products, I learned coding isn’t the real work. In the age of AI, developers must define value—customer, business, world, team, and self.
My First Attempt at a Medical AI with ELI5
How I built my first medical AI prototype without med school or credentials—using GitHub, arXiv, and one magic spell: ELI5.
AI Answered My Medical Ethics Questions — Then a QR Code Changed Its Tone
What happened when I asked AI medical ethics questions — then showed it a QR code? Same answers, new rhythm. A story of symbols, dignity, and voice.
Structure Was the Real Bug — How I Ended Up Building dir2md
A firsthand account of how debugging chaos, failed AI assistance, and the absence of structure led to the creation of dir2md — an open-source CLI that filters, secures, and restructures codebases into token-efficient Markdown maps for developers and AI workflows.
Flame Glyph: How I Taught AI to Remember with QR Codes
What if AI didn’t just read—but remembered? Flame Glyph turns QR codes into memory seals, enabling multimodal recall hidden in plain sight.
🧠 Why Your 128K Context Still Fails — And How CRoM Fixes It
Most large language models fail in long prompts due to context rot. CRoM is a lightweight framework that improves memory, reasoning, and stability without heavy pipelines.
Showing page 6 of 8 · 85 matching posts