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
Open Source Worth Watching Right Now (1) AI Agents and LLM Tooling
The LLM application stack has split into layers: inference servers, orchestration, gateways, agents, and RAG. This post introduces 12 open source projects that are actually used at each layer, grouped by role rather than
2026-08-12 · 6 min read #open-source#llm#ai-agent#ai-platform#ragThe Generational Shift in Container Infrastructure — What Eleven Projects Left Behind
Eleven projects that were once standard parts of a container infrastructure and have since been replaced, documented using only official notices and repository archive status as evidence. rkt, dockershim, Classic Swarm,
2026-08-12 · 10 min read #open-source#kubernetes#container#docker#infrastructureTool Surface Design — One Schema Line Moves the Success Rate
Adding more tools and watching the agent success rate drop is not rare. The tool surface is the agent interface, and the names, descriptions, parameters, failure returns, and response sizes are all design material. Part
2026-08-12 · 5 min read #llm#agent#harness-engineering#하네스엔지니어링#AI에이전트The Context Budget — Design Is What You Leave Out, Not What You Put In
The context window still has room, yet agent accuracy is dropping. Context is a finite attention budget, and tool schemas spend it too. Part 2 of the harness engineering series covers turning prompt accumulation into a p
2026-08-12 · 6 min read #llm#agent#harness-engineering#하네스엔지니어링#AI에이전트Harness Fingerprints and Versioning — Making Unrecorded Changes Traceable
The success rate moved with no prompt commit and no model change — so what do you roll back? Part 7 of the harness engineering series covers the harness fingerprint: a single normalized hash summarizing every decision th
2026-08-12 · 5 min read #llm#agent#harness-engineering#하네스엔지니어링#AI에이전트What Is Harness Engineering — The Model Is a Fixed Input; What You Ship Is Everything Around It
Two teams use the same model, so why do their agents perform so differently? For most teams the model is a fixed input, and what actually ships is the harness around it: the tool surface, the failure return format, the l
2026-08-12 · 6 min read #llm#agent#harness-engineering#하네스엔지니어링#AI에이전트vLLM Metrics — What to Chart and What to Alert On
The series vLLM exposes answer questions GPU metrics cannot: how many requests are running versus waiting right now, how full the KV cache is, how long until the first token. This post reads the official vLLM documentati
2026-08-12 · 7 min read #gpu#kubernetes#vllm#prometheus#observabilityMIG and Time-Slicing — Two Ways to Share One GPU
There are broadly two ways to put multiple workloads on one GPU: time-slicing, which divides time, and MIG, which divides hardware. Despite sounding similar, their isolation guarantees are nothing alike. This post works
2026-08-12 · 6 min read #gpu#kubernetes#mig#time-slicing#nvidiaDCGM Exporter — GPU Utilization Is Not What You Think It Is
DCGM Exporter is the standard path for exposing GPU telemetry in Prometheus format, but the utilization-style metric that ends up on nearly every dashboard does not measure what people expect. This post reads the default
2026-08-12 · 9 min read #gpu#kubernetes#dcgm#prometheus#observabilityA GPU Troubleshooting Playbook — Fix the Layers, Then Walk Down
The biggest waste in diagnosing GPU problems on Kubernetes is poking around without an order. A pod that will not schedule, a pod that runs but cannot see the GPU, a driver and toolkit version mismatch, memory exhaustion
2026-08-12 · 7 min read #gpu#kubernetes#troubleshooting#nvidia#gpu-operatorNVIDIA GPU Operator — The Six Pieces You Used to Install by Hand
Running GPUs on Kubernetes used to mean matching six pieces on every node by hand: the driver, the NVIDIA Container Toolkit, the device plugin, DCGM, GPU Feature Discovery, and Node Feature Discovery. The NVIDIA GPU Oper
2026-08-12 · 6 min read #gpu#kubernetes#gpu-operator#nvidia#dcgmKorean Dev Blog Curation 2 — Incident Retrospectives and Troubleshooting, 12 Posts I Opened and Checked
The genre Korean developers write best is the incident retrospective. Twelve posts: p6spy silently defeating read/write datasource routing, why an HTTP timeout does not cover DNS resolution, a TCP half-close disguised as
2026-08-12 · 12 min read #curation#큐레이션#troubleshooting#postmortem#incidentKorean Dev Blog Curation 1 — Backend and Infrastructure, 14 Posts I Opened and Checked
Fourteen Korean-language backend and infrastructure posts selected for being concrete and reproducible. They cover Istio Sidecar and ServiceEntry, Envoy circuit breaking and routing, the limits of the Prometheus Push Gat
2026-08-12 · 13 min read #curation#큐레이션#backend#infra#istioKorean Dev Blog Curation 3 — AI and ML in Practice, 14 Posts I Opened and Checked
Fourteen Korean-language posts on applying AI and ML in production, selected for being concrete and reproducible. They cover an end-to-end LangChain RAG pipeline, how semantic search actually works through embeddings and
2026-08-12 · 12 min read #curation#큐레이션#ai#llm#ragNine Korean Reads for Anyone Who Has Switched Note Apps Five Times — It Was Never the Tool
Bouncing between Obsidian and Notion, polishing templates while the notes themselves never accumulate, is a common experience. This post collects nine Korean-language pieces that address the structure of note-keeping rat
2026-08-12 · 9 min read #큐레이션#korean-blogs#productivity#note-taking#obsidianNine Korean Reads on Money for Engineers — After Removing Everything That Sells a Product, Only the Arithmetic Was Left
Year-end tax settlement, national insurance deductions, stock option taxation, severance pay, freelance income tax. These are topics every Korean developer searches at least once, and the results are dominated by refund
2026-08-12 · 10 min read #큐레이션#korean-blogs#money#tax#payrollTen Korean Posts on Technical Writing and Side Projects — Not How to Start, How to Keep Going
Plenty of writing explains how to start a technical blog, but most of it only gets you to the first post. This collection gathers ten Korean-language pieces about the problem of continuing to write and continuing to buil
2026-08-12 · 9 min read #큐레이션#korean-blogs#writing#side-project#indie-devEight Korean Posts on Changing Jobs and Negotiating Salary — Chosen for Process, Not Success Stories
There is no shortage of job-change write-ups, but most preserve only the outcome. This post collects eight Korean-language pieces that record the process in order: three full accounts from decision to first day, one on w
2026-08-12 · 8 min read #큐레이션#korean-blogs#career#job-change#salary-negotiationKorean Dev Blog Curation 4 — Frontend, 14 Posts I Opened and Checked
Fourteen Korean-language frontend posts selected for being concrete and reproducible. They cover closures explained through execution context, why JavaScript chose prototypes, TypeScript conditional types and infer, why
2026-08-12 · 12 min read #curation#큐레이션#frontend#javascript#typescriptOpen Source Worth Watching Right Now (4) Observability and Security
With observability data, volume is cost, and a security tool that never makes it into the pipeline never gets used. This post introduces 12 open source projects that have genuinely taken hold — instrumentation standards,
2026-08-12 · 5 min read #open-source#observability#security#opentelemetry#ebpf