LLM

I built a system with DuckDB, and Streamlit to monitor and manage energy prices for better control and planning LLM jobs during winter

Notes from testing DeepSeek-OCR as a local vision-language model for OCR and text compression on a large archive of screenshots. Includes observations on model performance, visual-token compression, and multilingual results.

A brief look at Gemini Pro 2.5 compared with ChatGPT 5 and Claude Opus/Sonnet, plus notes on Gemini 2.5 variants, NotebookLM, and mobile privacy concerns.

There is a lot of synthetic data that is being generated by LLMs, These include false metrics.

OpenAI’s removal of GPT-4o, o3, and other models after GPT-5’s launch breaks fundamental MLOps principles. Without model versioning and control, data science workflows become unreliable. Local LLMs offer a better alternative for maintaining consistency.

How the Mac Mini M4 has enabled affordable Local LLM inference and making VRAM-starved NVIDIA cards obsolete for low power and low cost

Around October 2024, The infamous “How many R’s are in strawberry?” question has become a fascinating litmus test for Large Language Models, exposing a fundamental limitation in how these systems process text.

Artificial Intelligence Applications in Financial Services with a demo on Local LLM Invoice Processing with Automated Billing Code Assignment

Understanding why handling multiple requests beats raw token speed for my local LLM deployments.