Blog
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 3517 posts
#2026-03 765#english 592#culture 264#deep-dive 254#kubernetes 247#career 229#ai 216#llm 208#devops 193#2026-04 146#security 141#database 114#observability 113#communication 109#history 107#architecture 100#productivity 96#finance 88#economy 84#mindset 81#psychology 80#ai-papers 79#food 78#it 78#travel 78#deep-learning 77#japanese 77#networking 77#performance 72#business-travel 70#linux 70#gpu 69#ai-agent 66#cs-fundamentals 63#postgresql 60#rag 58#self-improvement 55#learning 53#mlops 53#ai-platform 51
LLM Hallucination: Why AI Makes Things Up and 5 Strategies to Prevent It
A technical deep-dive into why LLMs hallucinate, covering all four hallucination types and five practical prevention strategies including RAG, self-critique pipelines, Chain of Verification, and temperature tuning — all
2026-03-18 · 9 min read #hallucination#llm#ai-reliability#ai-development#rag1 Million Token Context Windows: Is RAG Becoming Obsolete?
With Gemini 1.5 Pro's 1M token context and Claude's 200K, many developers ask: why bother with RAG? We compare real costs, latency, and quality to give you an honest answer.
2026-03-18 · 6 min read #context-window#rag#llm#long-context#ai-developmentGraphRAG Complete Guide: How Knowledge Graphs Overcome RAG Limitations
Standard RAG fails on global queries like "summarize the key risk themes across all these documents." We walk through how Microsoft Research's GraphRAG solves this, with real code and honest cost analysis.
2026-03-18 · 8 min read #graphrag#knowledge-graph#rag#microsoft#ai-developmentFine-tuning in Practice: Building Your Own Model with LoRA and QLoRA
You don't need 7 H100s. With LoRA and QLoRA, you can fine-tune a 70B model on a single consumer GPU. A practical end-to-end guide with working code.
2026-03-18 · 7 min read #fine-tuning#lora#qlora#llm#ai-developmentDeveloper Career Strategy in the AI Era: A Realistic 5-Year Roadmap
Moving past the fear of AI replacing developers, this post offers an honest look at the real situation and concrete career strategies to prepare for the next five years.
2026-03-18 · 7 min read #developer-career#ai-era#career-strategy#developer-growth#ai-developmentOne Must Imagine the Developer Happy: Camus, Sisyphus, and Repetitive Work
Albert Camus' 1942 essay on Sisyphus offers the most honest philosophy of repetitive work ever written. The bug queue that never empties, the codebase that always needs refactoring, the sprint that never truly ends — and
2026-03-18 · 10 min read #camus#sisyphus#absurdism#repetitive-work#philosophyAristotle's Eudaimonia: A Philosophy of Flourishing for Developers
Aristotle's concept of Eudaimonia (εὐδαιμονία) offers developers a framework for genuine flourishing — not just pleasure, but a life of excellence, meaningful relationships, and purposeful work.
2026-03-18 · 15 min read #aristotle#eudaimonia#happiness#philosophy#developerAMD GPU & ROCm Deep Dive: Can It Challenge CUDA for LLM Inference?
A thorough technical analysis of AMD MI300X with 192GB HBM3, the ROCm software stack, and HIP programming model. Includes real LLM serving benchmarks with vLLM and llama.cpp, and an honest assessment of strengths and wea
2026-03-18 · 14 min read #amd#rocm#gpu#mi300x#model-servingFAANG Behavioral Interview Complete Guide: STAR Method and Leadership Principles
A comprehensive guide to mastering FAANG behavioral interviews. Covers the STAR method, all 14 Amazon Leadership Principles, Google and Meta interview characteristics, Top 30 frequently asked questions, and elevator pitc
2026-03-17 · 17 min read #faang#behavioral-interview#star-method#아마존리더십원칙#구글면접MLOps Complete Guide: From ML Pipeline to Production Deployment
The complete guide to MLOps. Master ML pipeline design, experiment tracking (MLflow, W&B), model registry, CI/CD, model serving, and monitoring with real-world examples.
2026-03-17 · 22 min read #mlops#ml-pipeline#kubeflow#mlflow#wandbAI Model Serving and Inference Optimization Complete Guide: vLLM, TensorRT, Triton, Ollama
The complete guide to efficiently serving AI models in production. Master vLLM, TensorRT, NVIDIA Triton Inference Server, Ollama, quantization (INT8/INT4), batch processing, and latency optimization with real-world examp
2026-03-17 · 19 min read #mlops#model-serving#vllm#tensorrt#tritonComplete Guide to AI Model Deployment & Serving: Triton, vLLM, BentoML, and Kubernetes
A production-ready guide covering Docker GPU containers, Kubernetes HPA, NVIDIA Triton, vLLM LLM serving, BentoML, and Ray Serve for deploying AI models at scale.
2026-03-17 · 12 min read #modelserving#triton#vllm#bentoml#kubernetesFreeBSD Jails, ZFS, and Practical Server Operations
A practical guide to running FreeBSD in production, covering why teams still choose it, how jails differ from containers, how ZFS changes operations, and which runbooks matter most for long-lived servers.
2026-03-17 · 4 min read #freebsd#zfs#jails#server-operations#linuxPrometheus in Production: TSDB, Cardinality, Recording Rules, Federation, and Remote Write
A practical Prometheus operations guide covering TSDB retention, high-cardinality control, recording and alerting rule design, and when to choose federation versus remote write.
2026-03-17 · 5 min read #prometheus#observability#tsdb#cardinality#recording-rulesFAANG System Design Interview Complete Guide
A comprehensive guide to mastering FAANG system design interviews. Covers the RESHADED framework, URL Shortener, Twitter Feed, YouTube Streaming, Chat System design examples, and company-specific question trends.
2026-03-17 · 16 min read #system-design#faang#면접#대규모시스템#distributed-systemsKCSA Kubernetes and Cloud Native Security Associate Practice Exam: 60 Questions
A full 60-question KCSA practice exam covering all domains: Cloud Native Security Overview, Cluster Component Security, Security Fundamentals, Threat Model, Platform Security, and Compliance Frameworks. Complete preparat
2026-03-17 · 29 min read #kubernetes#kcsa#cncf#kubernetes-security#certificationKubernetes CKAD Certification Practice Exam (55 Questions + 10 Practical Simulations)
Comprehensive CKAD (Certified Kubernetes Application Developer) practice exam with 55 multiple-choice questions and 10 hands-on practical simulations covering application design, deployment, observability, configuration/
2026-03-17 · 28 min read #kubernetes#ckad#certification#applicationdevelopment#devopsComplete Guide to Open Source LLMs: Llama 3, Mistral, DeepSeek, Qwen, and Gemma
A comprehensive overview of the open source LLM landscape covering Llama 3, Mistral, DeepSeek, Qwen, and Gemma.
2026-03-17 · 14 min read #llm#llama#mistral#deepseek#qwenComplete Guide to LLM Evaluation and Benchmarking: MMLU, MT-Bench, RAGAS, LM-Eval
A complete guide to evaluating LLMs correctly. Covers standard benchmarks such as MMLU, MT-Bench, and HumanEval, evaluating RAG systems with RAGAS, practical use of LM-Evaluation-Harness, and building production LLM eval
2026-03-17 · 17 min read #llm#evaluation#benchmark#ragas#lm-evalBuilding LLM from Scratch: Complete Guide to Understanding GPT through Code
A complete guide to building and understanding Large Language Models from scratch. Implement a full GPT architecture in PyTorch — from tokenizer to Transformer, pretraining, and fine-tuning.
2026-03-17 · 21 min read #llm#gpt#transformer#from-scratch#deep-learning