POSTS / ARCHIVE

All posts
in order.

Everything I've written, newest first. Roughly one post per shipped milestone or learned lesson.

2026 5 POSTS
2025 7 POSTS
01

I Let Two AIs Talk to Each Other for 500 Turns. It Got Weird.

What happens when you let two local LLMs have unsupervised conversations? Cosmic harmony engines, fictional PhD consultants, and a surprisingly deep discussion about why chickens cross roads.

AISLMMulti-Model ArchitectureLLM
17 DEC 2025 10 MIN · SLM RESEARCH
02

When the SDK Says No: Vision-Aware RAG via a 300-Line Python Bridge

After CLIP made multimodal search instant, I hit a wall: the LLM could find images but couldn't see them. Here's how an Oracle engineer's tip and 300 lines of Python broke through.

AIOracle Database 26aiGrok-4Vision AI
22 NOV 2025 15 MIN · BUILDING A KNOWLEDGE MANAGEMENT APP WITH ORACLE AI DATABASE 26AI
03

Three LLMs, One App: Balancing Speed, Privacy, and Power

Testing LLMs in an Oracle Database 23ai app: cloud (OCI), laptop (M2 Mac), and GPU server (RTX 5090). Spoiler: My laptop needs a bigger GPU!

AILLMPerformanceArchitecture
28 OCT 2025 6 MIN · BUILDING A KNOWLEDGE MANAGEMENT APP WITH ORACLE AI DATABASE 26AI
04

Fine-Tuning a Personal Executive Assistant: Lessons from My Management Notes

How I fine-tuned IBM Granite 4.0 H Micro on 5+ years of management notes to create a personalized AI assistant—after three failures, the key was data quality.

AISLMFine-tuningGranite
05 OCT 2025 8 MIN · SLM RESEARCH
05

Fine-Tuning Qwen Models: From Theory to Practice

Fine-tuning Qwen 32B and 14B models to create ChefBot—a cooking AI that outperforms general-purpose LLMs in the kitchen.

AISLMFine-tuningQwen
29 SEP 2025 3 MIN · SLM RESEARCH
06

Building the RTX 5090 AI Workstation - Step by Step | Part 2

A detailed walkthrough of assembling my RTX 5090-powered AI workstation with photos from the entire build process

AIRTX 5090HardwareBuild Process
24 SEP 2025 3 MIN · BUILDING AN SLM POWERHOUSE
07

Building the Ultimate AI Workstation | Part 1

Planning an RTX 5090 AI workstation for fine-tuning specialized language models. Part 1 covers goals, component selection, and the SLM thesis.

hardwareAIMLRTX 5090
20 SEP 2025 3 MIN · BUILDING AN SLM POWERHOUSE
2024 1 POSTS