Distributed Thinking Systems Blog
A structured writing hub for local-first AI, secure automation, developer tooling, family-law analysis, and project updates.
For related project work, start with Secrets Kit, LLM Ops Kit, and Case Analytics.
All Posts
Browse the complete chronological archive across the main blog, series, Hands-On articles, and project blogs.
Browse All PostsTechnology
Practical work on AI systems, local LLMs, Python tooling, debugging, and the infrastructure behind it.
Read Technology PostsSeries
Long-form article series that follow an engineering problem across design, implementation, measurement, and operations.
Browse SeriesHands-On
Runnable tutorials and focused implementation exercises drawn from the site's engineering work.
Read Hands-On PostsParental Alienation
Writing on parental alienation, research, and the real-world impact around it.
Read Parental Alienation PostsBrowse by Topic
Use the Topics index to explore tags and cross-project themes spanning site posts and project blogs.
Recent from Technology
-
Tuning Codex Subagents for the Work They Actually Do
My Codex subagents have different jobs, models, and reasoning settings. That helps me route work sensibly, but spawning more agents is not a magic token discount.
-
When Codex Needed the Whole ChatGPT Conversation, It Turned to LogGPT
I asked Codex to move a long ChatGPT Work conversation into a development project. It chose a Safari extension I’d written and recovered 1,651 messages and 97 artifacts. I hadn’t told it to use LogGPT.
-
Pulling the Plug Isn't an AI Containment Strategy
Temporary AI agents can leave behind persistent knowledge, coordinate with other agents, and rebuild communication paths. That makes containment a systems problem, not a power-switch problem.
Recent from Series
-
Hands-On: Keep a One-Page Publication Record
Copy a compact publication record and follow an invented series post from local review to the public page and reader-response routes.
-
Closing the Publishing Loop Without Pretending It Is a CMS
Three kinds of writing enter this Jekyll site, but they all need the same human decision before a push and the same public checks afterward. The reader can then respond in a discussion or through a mail-client draft.
-
Hands-On: Check What the Deployed Site Serves
Serve an invented miniature site on loopback and see the difference between a missing asset, a successful HTTP response, and a redirect to the right page.
Recent from Hands-On
-
Hands-On: Keep a One-Page Publication Record
Copy a compact publication record and follow an invented series post from local review to the public page and reader-response routes.
-
Hands-On: Check What the Deployed Site Serves
Serve an invented miniature site on loopback and see the difference between a missing asset, a successful HTTP response, and a redirect to the right page.
-
Hands-On: Build a Small Prepublication Check Runner
Run three small gates against an invented article, break one input at a time, and watch the runner stop without touching a real Jekyll checkout.
Recent from Parental Alienation
-
Parental Alienation Awareness - Introduction
Welcome to the Parental Alienation Awareness project blog. Here we share research-based insights on the scope, impact, and damage of parental alienation to children, families, and society.
-
Harnessing AI for Change: The Next Chapter for Distributed Thinking Systems
Parental alienation is a slow, insidious process, often unfolding in subtle shifts of language, repeated patterns of exclusion, and emotional manipulation hidden within everyday communication. The words that once carried love and trust become barriers, severing bonds between parents and children. For those affected, the experience is devastating. The pain lingers, compounded by the fact that so often, the signs go unnoticed until it is too late.