Blogs
Thoughts, insights, and tutorials on web development and modern technologies.
Filter by tags
AI
Deep Learning
GPU
Hallucination
Inference
LLM
Machine Learning
RAG
Training
VRAM
Understanding GPU VRAM
2025-11-09
Ever wondered why your ML model won't fit on your GPU? Learn how to calculate VRAM requirements for training and inference, understand the difference between FP32, FP16, and INT8, and discover practical formulas with real-world examples for models from BERT to LLaMA.
Machine Learning
GPU
VRAM
Deep Learning
AI
Training
Inference
Stop Your AI From Lying: Reduce Hallucinations
2025-06-19
Your AI sounds confident, but is it telling the truth? Learn battle-tested techniques to cut hallucinations in production and stop losing user trust to confidently wrong AI responses. Proven methods: RAG implementation, smart prompting, system guardrails, and real case studies from developers who've solved this problem.
AI
LLM
Hallucination
RAG
Machine Learning