Debug and Rebug: The Records of a Developing Developer

Tech Log Entry — Browser Image Agent:  An AI-Powered Image Tagger and Saver Category: AI / Computer Vision / Browser Automation / Local LLM / Python Initial Goal I wanted a tool to automatically save images from open browser tabs to a local folder, with descriptive, search-friendly filenames and tags generated by an AI vision model — replacing manual save-and-rename workflows. All processing to be fully local: no cloud APIs, no subscriptions, no data leaving the machine. The tool should use only free open-source software, run on my Windows 11 desktop, and leverage my RTX 3060 GPU for local AI inference. Two operating modes: fully automatic (save all qualifying images without interruption) and human-in-the-loop review (confirm each image before saving). Hardware Used Desktop: Windows 11 Home, NVIDIA GeForce RTX 3060 (12 GB VRAM) No additional hardware required — everything runs locally on the desktop Software Stack Python 3.12 Ollama 0.17.7 (local AI runtime) Vision mode...

Obsidian Setup ( Tech Studies Log) Date: March 19, 2026 Learned how to install and use Obsidian on my Windows desktop (Linux laptop will be this weekend) and created the local vault on my D: drive.  Basic folder structure setup for my knowledge system: 00 Inbox 01 Notes 02 PDFs 03 Web Clips 99 Templates Most documents at this stage are going to be PDFs from webpages. I configured attachments to go into the 02 PDFs folder. I enabled the Templates core plugin and created a reusable PDF Source Template for notes based on saved PDF files. I tested how to insert the template into a note; also confirmed that template variables and note structure worked as intended. I also added several PDF files into the vault and linked a PDF to a note. I confirmed that clicking the link opens the PDF inside Obsidian. I learned how to: link a PDF file inside a note point to a specific PDF page embed a specific PDF page directly into a note add comments under important...

Tech Log Entry — Direct Ethernet File Transfer: Windows 11 Desktop to Linux Mint Laptop Category: Networking / File Transfer / Cross-Platform Initial Goal I wanted to replace the use of USB stick drives and email as file transfer methods between my desktop (Windows 11 Home) and laptop (Linux Mint Cinnamon).  Taking too long; too inefficient. Establish a fast, direct, private Ethernet connection not dependent on the home WiFi router (for best practices in privacy and security). Primary direction: desktop → laptop, with occasional reverse transfers.  Most of my work is done on the desktop w/ 2 monitors.  Laptop is mostly for out-of-home work, and Linux studying, etc. Hardware Used TP-Link UE306 USB 3.0 to RJ45 gigabit Ethernet adapter (laptop has no built-in Ethernet port) Cat8 Ethernet cable (4ft) for direct desktop-to-laptop connection (no docking station) Desktop's built-in Ethernet port LLM Used Claude 4.6 (non-extended thinking) IP Addresses Assigned (Dire...

Tech Log Entry — Regarding Windows Media Player Legacy (WMPL) - The Task of Enhancing Privacy & Conducting Cleanup   Category: Cybersecurity / Privacy / Windows 11 Initial Issue Desktop was visible as a Media Device on the home network WMPL had automatically indexed personal photos, videos, and other media files without user knowledge or intentional setup Files were potentially discoverable by other devices on the shared home WiFi, including DirecTV equipment Discovery Found desktop system listed under Network → Media Devices in File Explorer Clicking the DirecTV2PC Media Server entry launched WMPL and revealed personal files in its library Confirmed WMPL had auto-populated its library from watched folders without user action Investigation Steps Checked WMPL Stream menu — media streaming was already off in WMPL itself Identified the real issue: OS-level network sharing services were broadcasting the device Located WMPL's database files at: C:\Users\[username]\AppData...

Using an LLM as a database:  From Wikipedia:  "BASE stands for [B]asically [A]vailable, [S]oft state, and [E]ventually consistent: the acronym highlights that BASE is opposite of ACID, like their chemical equivalents. ACID databases prioritize consistency over availability — the whole transaction fails if an error occurs in any step within the transaction; in contrast, BASE databases prioritize availability over consistency: instead of failing the transaction, users can access inconsistent data temporarily: data consistency is achieved, but not immediately." LLMs use context windows to interface between their pre-training and RAG knowledge-bases and the user with whom they are interacting.  The context window is soft-state, and it vanishes to nothing when it is no longer needed.  That is, after it is either abandoned or filled up to capacity. The BASE approach to databases is the linear opposite, in all four (4) dimensions, from the ACID approach.  Nearly all da...

Who Is Responsible For A.I. Doing Damage? Who Is Responsible When A.I. Tools Help Commit Crimes? (right now) Social media companies: "Hey, we just provide the platform. We're not responsible for what people put on it or how they use it." (very soon) AI companies: "Hey, we just provide the intelligence. We're not responsible for what people put into it or how they use it." Maybe some of that "very soon" with AI companies...is happening now?  How many of the largest such companies have already had that discussion in some conference room or boardroom? A.I. Ethics is a growing field, and one that seems to be a very small part of the overall chatter of the world's fast-paced development of AIs. It seems LLMs and the like are a powerful means to diffuse out (or absolve entirely) responsibility in ethnics, law, and morality.