Samsung 4nm process: betting on maturity for AI and HBM4 https://sudonull.com/samsung-4nm-process-betting-on-maturity-for-ai-and-hbm4
Samsung expands production using mature 4nm FinFET process for AI chips, HBM4, and autonomous driving. Learn why stability is taking center stage in the semiconductor technology race.
LLM Hallucinations: Data Compression Artifacts https://sudonull.com/llm-hallucinations-data-compression-artifacts
Breaking down LLM hallucinations through lossy compression: why they occur, how to minimize with RAG and fine-tuning. For developers: Shannon's theory and examples. Learn how to work with artifacts.
Fine-tuning Gemma 4 on Cloud Run with GPU https://sudonull.com/fine-tuning-gemma-4-on-cloud-run-with-gpu
Instructions for fine-tuning Gemma 4 31B on Cloud Run Jobs for image classification. QLoRA, LoRA rank 64, accuracy 94%. For middle/senior developers. Start fine-tuning now.