Blog on Thede Technologies

The Architecture of Advice: Inside the AI High-Fidelity Loop

Mon, 11 May 2026 00:00:00 +0000

In the last post I looked at the sheer volume of AI-assisted engineering: 55,000 turns of professional capital recovered from a single month. But once you have the data, you stop asking “how much?” and start asking “what kind?”

So I ran a high-fidelity thematic enrichment pass over 466 sessions from the corpus and started mapping what I’m calling the architecture of advice: the hidden patterns that define how AI actually influences a multi-repo technical portfolio.

30 Days of AI Collaboration: Recovering 55,000 Turns of Professional Capital

Thu, 07 May 2026 00:00:00 +0000

In the spring of 2026 I spent 30 days living in the “jagged frontier” of AI-assisted software engineering.

If you’ve worked with Claude Code, Gemini CLI, Cursor, or Codex you know the feeling. A high-intensity session ends, the terminal clears, and months of architectural decisions, hard-won debugging insights, and technical pivots vanish into the ephemeral void of chat history. The next morning you remember the outcome but not the reasoning that got you there.

Getting good output from Lens: the model and LM Studio settings matter more than you think

Tue, 05 May 2026 00:00:00 +0000

A Lens daily summary derailed by reasoning artifacts — **People:**, **Patterns:**, **Drafting structure:**, “Constraint Check” — bleeding into the narrative

People pick up Lens , connect it to LM Studio, point it at whatever model they downloaded first, and expect polished daily snapshots. Sometimes they get them. Sometimes the same setup on a different machine produces output that reads like the model thinking out loud — or worse, fabricating events that didn’t happen.

Four frontier models, one year of office sensor data, four very different dashboards

Wed, 29 Apr 2026 00:00:00 +0000

I have an Adafruit Clue sensor sitting on the desk in my home office. It has been quietly logging temperature, humidity, pressure, light, sound, and color every thirty seconds for a little over a year. 425,000 readings. About 33 megabytes of CSV. (I wrote up the build itself a year ago — CircuitPython on the device, a Python pywebview gateway on the Mac, USB Serial in between.)

I finally fed that year of data to four frontier models and asked each of them to build me a single self-contained HTML dashboard. Same prompt. Same data. Four very different answers.

The move was upstream

Tue, 28 Apr 2026 00:00:00 +0000

I spent most of a day pointing at broken cases. Each time I pointed at one, the model patched it. The next regeneration would surface a different broken case in a different file. We’d patch that. Then a third. By late afternoon I was the one suggesting we slow down and return to first principles — the model wasn’t pulling me up a level on its own.

The bug itself was small. I’ve been wiring up a pipeline that turns transcripts of my conversations with AI tools into clean Markdown for an Obsidian vault. The reasoning part — extracting topics, summarizing, tagging — was working. The rendering kept breaking. Stray characters, broken callouts, content that ended up harder to read than the original conversation had been. I was working it inside Gemini CLI, mostly on their fast tier with occasional escalation to their reasoning model. Twelve back-and-forth turns across roughly six hours of intermittent work, and we still hadn’t landed it.

The race nobody else is running: why personal AI belongs on hardware you already own

Mon, 27 Apr 2026 00:00:00 +0000

Tim Cook stepped down this week. The next CEO of Apple is John Ternus, the hardware engineer who ran the Mac transition to Apple Silicon. The new Chief Hardware Officer is Johny Srouji, who built the chips that made the transition possible. Two hardware people at the top of the company, at the exact moment the cloud AI labs are quietly losing money on their best customers.

Nate B. Jones made the case that this is Apple declining the race the rest of the industry is running and lining up for a different one. I think he’s right, and I want to add what I can only add from inside it: this is the race I’ve already been running on a four-year-old machine under my desk, and the people I trust are starting to run it too.

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.

The Memex Has Been Waiting 80 Years for This Moment

Sat, 11 Apr 2026 00:00:00 +0000

In July 1945, an engineer named Vannevar Bush published an essay in The Atlantic called “As We May Think.” It is one of the strangest, most hopeful documents I know.

Bush had spent the war as the director of the U.S. Office of Scientific Research and Development. He oversaw the entire American scientific war effort — radar, the proximity fuse, penicillin manufacturing, and, indirectly, the work that would end the war the same month his essay was published. The atomic bombs fell on Hiroshima and Nagasaki in August 1945. Bush’s essay came out a few weeks earlier. He could feel what was coming. He wrote the essay anyway, and what he wrote was not a triumphal account of what science had done. It was a quiet, almost embarrassed argument that the same instruments scientists had built for destruction could be turned, just as easily, toward the preservation of human knowledge.

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.

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.

From idea to IoT data: building an environmental monitor with Adafruit Clue and Python

Tue, 08 Apr 2025 00:00:00 +0000

This post was originally published on officeofadamthede.com on April 8, 2025. I’m consolidating it here because the data this Clue has been quietly logging ever since became the dataset behind a bake-off post a year later — capture solved here, synthesis explored there.

Have you ever had an idea for a connected device, something that could sense the world around you and share that data? I recently embarked on such a journey, diving headfirst into the Internet of Things (IoT) with the goal of creating an environmental data logger using the versatile Adafruit Clue board. As someone relatively new to both IoT hardware projects and Python, this was an exciting, challenging, and ultimately very rewarding experience, made significantly faster and more manageable with the help of AI development tools.