Thede Technologies

A general-purpose MoE multimodal beat every dedicated vision model on my father's handwriting

Thu, 23 Apr 2026 00:00:00 +0000

I’ve been transcribing a multi-generational archive of handwritten family letters on my own hardware. Posts one and two covered why and how. This post is the surprise.

I assumed the right tool for a vision task was a vision model. If you’re reading handwriting, you reach for something labeled “VL.” If you can find one fine-tuned for OCR and handwriting, even better.

I was wrong — at least at the sizes I can run locally in 2026.

Running real models locally on a Mac Studio that isn't new anymore

Thu, 23 Apr 2026 00:00:00 +0000

I have a multi-generational archive of handwritten family letters in my house, and I wanted to read it without sending the private content to a cloud provider. The first post is the why. This one is the how — on the specific hardware I already own, with the software I landed on.

My Mac Studio is almost four years old. M1 Max, 64 GB of RAM. It’s proven more than capable of running large language models locally — it keeps private content in the house, and it’s significantly cheaper than any cloud provider.

What family archives are for, now that the AI can read them

Thu, 23 Apr 2026 00:00:00 +0000

I have three collections of letters sitting in my house.

The oldest is a stack from my great-grandparents, written between 1910 and 1913. The second is from my grandparents, written during World War II. The third is from my father — letters he wrote from the moment I was born until the moment his mother died.

Three generations, each one writing to the next, each one leaving behind something I’ve never fully read.

From Tools to Framework: What a Year of Agentic Development Actually Looks Like

Fri, 03 Apr 2026 00:00:00 +0000

Frameworks are inevitable.

Kevin Kelly wrote about this in What Technology Wants — that certain inventions appear independently, in multiple places, at roughly the same time. The telephone, the lightbulb, calculus. Not because of genius, but because the conditions were right. The substrate was ready and the solution was waiting to be found.

Ruby got Rails. Python got Django. PHP got Laravel. In each case, the same pattern: developers working with raw tools hit a ceiling, and someone assembled an opinionated structure that encoded what worked into something repeatable. The framework didn’t invent new capabilities — it organized the ones that already existed into a form that could be taught, shared, and built upon.

Context Architecture: Building the Library Your Agents Actually Need

Sat, 28 Mar 2026 00:00:00 +0000

Your AI agent isn’t stupid. It’s lost.

The most common failure I see in agentic systems isn’t a reasoning failure or a coding error. It’s a context failure. The agent didn’t have the right information at the right time, so it guessed. And the guess looked plausible enough that nobody caught it until production.

Context architecture is the skill of building structured data environments so that AI agents can reliably search, find, and retrieve exactly the information they need — without getting confused by dirty data, missing context, or irrelevant noise. Anthropic’s engineering team put it plainly: “Claude is already smart enough. Intelligence is not the bottleneck. Context is.”

Specification Precision: The Most Valuable AI Skill Isn't Technical

Sat, 28 Mar 2026 00:00:00 +0000

The most valuable skill in the AI economy isn’t coding. It’s writing.

Not blog posts or marketing copy. I mean writing instructions so precise that a literal-minded machine with no ability to read between the lines will execute exactly what you intended. Every time. Without you watching.

I’ve spent the last year building an AI-augmented engineering operation across 13 projects. The single biggest determinant of whether an agent produces good work isn’t the model, the temperature, or the prompt template. It’s the specificity of the instruction I gave it.

Eliminating Waste in the SDLC

Tue, 24 Mar 2026 00:00:00 +0000

When AI can use the same tools you use — Jira, GitHub, Sentry — the bottleneck in software development shifts from writing code to everything around the code. This talk applies the Toyota Production System’s waste-elimination framework to an AI-augmented development workflow, showing how MCP tool handoff, Gherkin specifications, and encoded quality gates systematically remove entire categories of waste from the software development lifecycle.

The System That Built Itself

Sat, 07 Mar 2026 00:00:00 +0000

I didn’t set out to build a system. I set out to survive.

For the better part of a year, I’ve been operating as a one-person engineering team — across my day job and the products I’m building on my own. I wrote about what that looks like in The One-Person Engineering Team , and about the engineering practices that emerged in Eliminating Waste in the SDLC . But something else happened that I didn’t fully recognize until I stopped and looked at what I’d built.

Eliminating Waste in the SDLC

Thu, 05 Mar 2026 00:00:00 +0000

I wrote a follow-up exploring what happens after you eliminate the waste: The Processing Layer Is Not a Moat .

I don’t write much code anymore.

About six months ago, Dario Amodei predicted that within a year, 90% of code would be AI-generated. More recently, Boris Cherny — the creator of Claude Code at Anthropic — said that 100% of his code was already written by AI. I thought those numbers sounded aggressive. Now I’m living them.

Whispering to the Machine: Take Two

Fri, 27 Feb 2026 00:00:00 +0000

Eight months ago, I wrote a snapshot of what it felt like to collaborate with AI in software development. I talked about using Cursor, chatting with models, migrating a codebase from Bootstrap to Tailwind. I laid out five principles: plan meticulously, work iteratively, use the right tool, embrace collaboration, don’t be afraid to start fresh.

Those principles still hold. Every one of them. But the way I execute on them has changed so dramatically that the original piece reads like a dispatch from a different era. Eight months in this field might as well be a decade.

The One-Person Engineering Team

Tue, 17 Feb 2026 00:00:00 +0000

Boris Cherny, the creator of Claude Code at Anthropic, recently wrote that “pretty much 100% of our code is written by Claude Code.” For him personally, it had been 100% for over two months — he doesn’t even make small edits by hand. He shipped 22 PRs in one day and 27 the day before, each one entirely written by Claude.

I think he’s right. And I think most engineering teams aren’t ready for what that means.

Whispering to the Machine: A Snapshot of AI-Powered Development in 2025

Mon, 16 Jun 2025 00:00:00 +0000

I had a conversation with another developer recently that left me feeling energized. We were kicking off a new project, and as we started talking about process, it became clear we were both arriving at similar conclusions about how to actually work with AI in software development. It was one of those moments that validates the path you’ve been on — making you realize you’re not just shouting into the void.

About

Mon, 01 Jan 0001 00:00:00 +0000

The Short Version

I’m Adam Thede — founder of Thede Technologies, a software company based in Nashville, Tennessee. I build AI-native products and operate a portfolio of software across life-tracking, knowledge management, and personal data infrastructure. The flagship is the Tractor & Silo ecosystem — a suite of privacy-first, personal life-tracking applications across web, iOS, and macOS — a project I’ve been working on since 2016.

Contact

Mon, 01 Jan 0001 00:00:00 +0000

Products

Mon, 01 Jan 0001 00:00:00 +0000

The Vision

Everything in the Silo ecosystem exists to produce a journal entry worth keeping and handing down. We organize life data around the 5Ws — Who, What, When, Where, and Why — because that’s how humans naturally remember.

The Legacy Test: “Will my children find this meaningful in 30 years?” — this guides every feature decision.

How the Harvest Works

Your life is the farm. Each app and service works a different field — your iPhone captures where you go, your Mac records what you’re working on, RescueTime measures your productivity, GitHub logs your code, Limitless and Omi transcribe your conversations.

Services

Mon, 01 Jan 0001 00:00:00 +0000

Builder First

My primary focus is building the Tractor & Silo ecosystem — privacy-first personal data infrastructure across web, iOS, and macOS. Everything I know about technical strategy, AI operations, and engineering leadership comes from building and operating my own products, not from advising from the sidelines.

I occasionally take on advisory work when the right opportunity comes along.

What I’ve Built Expertise In

Technical strategy & architecture — system design, data modeling, infrastructure decisions, and technology evaluation
AI-native operations — orchestrating AI agents across a full product portfolio, from code generation to autonomous workflows
Engineering leadership — code review standards, workflow optimization, and team scaling
Full-stack development — hands-on building across web, mobile, and desktop

If You’re Interested

I’m not actively taking on new engagements right now, but I’m always open to conversations — especially about AI operations, data ownership, and where agents actually create value in real organizations.