Posts

• 2026/02/04 Circuit Tracing: Finding Medical Features in Gemma 3
• 2026/01/24 What Does Medical VLM Actually See? Experiments with MedGemma and Sparse Autoencoders
• 2026/01/20 Fluent But Wrong: LLM and Healthcare
• 2026/01/16 Opening the Black Box: How to See What Your Vision Language Model is Actually Looking At
• 2026/01/14 Data Generating Process
• 2026/01/11 Building AI Agents with Multimodal Models: The Final Challenge
• 2026/01/10 Building AI Agents with Multimodal Models: Part 4
• 2026/01/08 Understanding Random Variables: A Practical Guide for Engineers
• 2026/01/08 Building AI Agents with Multimodal Models: Part 3
• 2026/01/07 OCR on Engineering Drawings with a 0.9B Vision-Language Model
• 2026/01/07 Building AI Agents with Multimodal Models: Part 2
• 2026/01/05 Building AI Agents with Multimodal Models : Part 1
• 2026/01/03 Why a 0.9B VLM can be a serious OCR engine
• 2026/01/02 Multimodal LLMs in Healthcare: What’s Actually Working
• 2025/10/15 When AI Radiologists Get Confused: The Critical Challenge of VLM Robustness in Medical Diagnostics
• 2025/09/17 A guide to LLM evaluation metrics
• 2024/11/13 Bayesian Optimization