Categories
2026
The 90 percent discount Claude — why model reliability has to be argued in economics, not mathematics

NVIDIA AnyFlow — video diffusion distillation that is not tied to a step count

Writing code by hand again — the architecture debt seven months of AI coding left behind

Two flavors of omni — one index to retrieve with, one framework to generate with

Dissecting Spec Kit — GitHub's toolkit for turning specs into executable artifacts

Inside korean-law-mcp — folding 41 government APIs into 17 MCP tools

popcon dev log #12 — Streaming zip downloads, persisting action cache, stabilizing credit pill

hybrid-image-search dev log #19 — Merged model pool of 246, admin gates, gpt-image-2 resolution, and Phase 1 error handling

Two Agent-Memory Architectures — MemPalace's Structured Index vs Hermes Agent's Self-Curating Scratchpad

The Claude Code Skills Explosion — What Five Repos in One Day Are Telling Us

Open-Weight Models, First Week of May 2026 — Zyphra ZAYA1, Gemma 4 26B A4B, Qwen 3.6 35B A3B

Microsoft qlib — The Quant Backbone LLM Agents Will Ride On

Learning Agents: Course or Catalog? Microsoft AI Agents for Beginners vs. Awesome LLM Apps

Anthropic's April 23 Postmortem — Three Overlapping Regressions and What Engineers on Claude Should Take Away

Weekly arxiv digest — five papers that re-examine the interfaces we take for granted

The First Wave of Local Inference Tooling — gpum v1.1.0 and TokenSpeed

Claude Code OS — A Bootable LiveUSB That Treats Claude Code as the Operating System

Anthropic's Teaching Claude Why — Reasoning Beats Demonstration, Blackmail Drops to 0%

The OS Layer for AI Coding Agents — agentmemory and agent-skills Land the Same Day

Next.js v16.2.6 — One Release That Closes 13 Security Advisories at Once

NEKOWORK — A Verified Autopilot for AI Code Changes

Why Fly.io's Machines Are Actually the Building Block for Everything

ToonOut and BiRefNet — How an Anime-Tuned Matting Model Hits 99.5% Pixel Accuracy

Pushing Qwen3.5-122B from 28.3 to 51 tok per second on a single DGX Spark

popcon Dev Log #11 — Credits System, R2 Migration, ToonOut, and a Brutal Redesign

OpenAI's 2026-05-07 Announcement Blast — Cyber Model, ChatGPT Ads, Trusted Contact, Realtime Voice, MRC Networking
OPENAI Privacy Filter Reversible — Not Anonymization, Recoverable Pseudonymization

Mapping the Claude Code Plugin Landscape — Harness, Permission, Knowledge Graph, Secret Vault, Usage Monitor

LiteRT-LM v0.11.0 — Gemma 4 MTP Doubles Mobile GPU Decode, Windows Goes Native

hybrid-image-search Dev Log #18 — OpenAI gpt-image-2 Joins, Model/Product Library, and Internal Permission Tiers

Google Cloud Fraud Defense — The Next Evolution of reCAPTCHA, From Friction Layer to Risk Engine

CODEX-R — A Micro Skill That Imports Claude Code Sessions Into Codex CLI

Three arxiv Papers That Drifted Through the Chat — Multiagent Debate, MIA, Husserlian Phenomenology

The LLMLingua Series — Microsoft's Underrated Prompt Compression Stack

public-apis at 433K Stars — Why an Awesome-List Classic Is Trending Again in the MCP Era

Polaris MCFG — A License-Safe Metric-Compatible Font Generator, Plus the LLM Eval Rubric Thread Next to It

Bun Is Being Ported From Zig to Rust — A 30KB PORTING.md That Claude Follows

Anthropic Leases All of SpaceX's Colossus 1 — What the Claude Rate-Limit Bump Actually Means

How OpenAI Keeps Voice AI Low-Latency — A Relay + Transceiver Architecture for WebRTC on Kubernetes

Simon Willison's Granite 4.1 3B Pelican Gallery — Why All 21 Quantizations Flopped Together

gc-tree — Global Context Above CLAUDE.md and AGENTS.md, Managed Like Git Branches

EKS AMI CVE-2026-31431 Copy-Fail — Patch Delay and the algif_aead Mitigation

Codex in ChatGPT — Realigning to a Unified Coding Agent, and the Python SDK That Opens Headless Automation

X Launches XChat — An Independent Messenger, and Immediate Privacy Pushback

trading-agent Dev Log #14 — Universe Expansion, Hard-Gate Loosening, Archived HOLDs

The Korean AI Emoji Landscape — Amoji, Stipop, LINE Creators, and Where PopCon Fits

The Economics of Migrating to Fly.io — Three Case Studies

RunPod Spot vs On-Demand — When the 50% Discount Is Worth the Interruption

Pylette — A Python Library That Makes Color Palette Extraction Boring (in the Best Way)

popcon Dev Log #10 — Google Login, Scheduled Availability, and Fly.io Production Deploy

hybrid-image-search-demo Dev Log #17 — HEX-Only Injection, Angle Category Split, Korean Prompt Extraction

Go Production Deployment — AWS ECS vs Cloud Run vs Fly.io

Claude Tuner — Stop Guessing Your Rate Limit, Start Tracking It

Claude Design, Tested on a Real Project — PopCon UI Refinement

Can You Really Sell ChatGPT-Made Emojis on KakaoTalk? A Three-Step Workflow That Actually Passes Review

ToonOut — A BiRefNet Fork That Finally Gets Anime Hair Right

The 20-Minute Mental Model of Full-Stack — Frontend, Backend, Database

popcon Dev Log #9 — SAM2 Restore Fix, rembg→matte Rename, Google Login Spec

hybrid-image-search-demo Dev Log #16 — Lens Preset Expansion, Hover Previews, OTLP Telemetry

damn-my-slow-kt — One CLI Command Turns KT SLA Clauses Into Monthly Refunds

Why Multi-Agent Orchestration Doesn't Work Well

trading-agent Dev Log #13 — Live Research Search, Agent Lifecycle Events

Project Glasswing and Claude Mythos Preview — Anthropic's Bet on Proactive Cybersecurity

popcon Dev Log #8 — Archive Page, Start-Frame Review, and BiRefNet VFX Recovery

Netflix VOID — Interaction-Aware Video Object Deletion

hybrid-image-search-demo Dev Log #15 — Removing Tone Count, Unifying A/B Naming

Google Magika — AI-Powered File Type Detection at Scale

Gemini 3.1 Flash TTS — From Reading Machine to Digital Voice Director

GBrain — Garry Tan's AI Agent Memory System

Fuzzy Canary — A Clever Anti-AI Scraping Trap Using Hidden NSFW Links

Exa MCP Server — AI-Powered Web Search for Every AI IDE

Drew Bent on Using AI Well: It's Not About Speed

AI4AnimationPy — Python Framework for AI-Driven Character Animation

AI Coding Agent Ecosystem Tools — openai-oauth and Happy

trading-agent Dev Log #12 — UI Padding, Overlay Text Polish, Research Chart Fix

Three Design Principles That Strip the AI Smell Off a Vibe-Coded Landing Page

Reverse-Engineering Gemini's SynthID — Spectral Analysis Beats a Closed Watermark

popcon Dev Log #7 — RunPod GPU Worker, BiRefNet Matting, Parallel Frame Inference

Measuring Claude Code's Hidden Token Tax — 11 Bugs, 30K Requests, One Flag Override

hybrid-image-search-demo Dev Log #14 — Clock Skew, S3-First Ref Cache, Attribute-Aware Injection

HarnessKit Dev Log #6 — Marketplace Version Sync to 0.4.0

BiRefNet — The High-Resolution Segmentation Model Quietly Beating rembg

agentsview — One Local Binary for Every AI Agent's Sessions and Costs

trading-agent Dev Log #11 — Settings Page, Command Palette, and shadcn/ui Migration

The Background Removal Library Landscape — BiRefNet, ViTMatte, MatAnyone, and Friends

RunPod Serverless vs Pods — When Each Wins for GPU Workloads

Reading the Claude Code Hidden Problem Analysis — 11 Bugs, Proxy Data, and a Quota Blind Spot

popcon Dev Log #6 — RunPod GPU Worker, Async Parallelization, and Custom Motion Prompts

Micro-PaaS Reality Check 2026 — Fly.io, Heroku, and Render

log-blog Dev Log #8 — URL Classifier Quality Bumps and Multilingual Taxonomy Path Fix

hybrid-image-search-demo Dev Log #13 — Multi-Tone Reactions, Angle/Lens Presets, and Production EC2 Cutover

Trading Agent Dev Log #10 — UI Overhaul: Tailwind v4 + shadcn/ui

RunPod Serverless GPU and the Open-Source Dev Tool Wave

PopCon Dev Log #5 — SAM2 Interactive Refinement and Video Model Upgrade

Hybrid Image Search Dev Log #12 — Reranking Pipeline Fixes, Dual-Batch Generation, Frontend Sprint

Deep Documentation Crawling with Firecrawl — Building a map-filter-scrape Pipeline

Comparing Open-Source AI Image Matting, Sharpening, and Upscaling Tools

Claude Code Ultra Plan and the Multi-Agent Orchestration Reality Check

Claude Auto-Permission Dev Log #1 — Hook-Based Auto-Permission System

Building a Bilingual Hugo Blog — Automated Korean-English Publishing Pipeline

Trading Agent Dev Log #9 — ATR Dynamic Stop-Loss and Investment Horizon Management

Running SAM 2.1 on Mac — Apple Silicon GPU Acceleration and Meta SAM 3 Comparison

PopCon Dev Log #4 — SAM 2.1 Interactive Segmentation and Cost Optimization

Log-Blog Dev Log #7 — Plugin Command Migration and Bilingual Cover Images

Is Software Engineering Really Dead? — AI Coding Hype vs Reality

Hybrid Image Search Dev Log #11 — Tone/Angle Injection UX and EC2 Deployment

HarnessKit Dev Log #5 — Architect Skill and Auto-Registration System

Claude Code + Figma Design Workflow — Consistent Design and Content Automation

Running a Free, Private AI Assistant — Gemma 4 + SearXNG + OpenClaw Setup Guide

PopCon Dev Log #3 — Background Removal and APNG Transparency Pipeline

Hybrid Image Search Dev Log #10 — OTel Metrics Dashboard and Pipeline Performance Optimization

Claude Code Power User Guide — Ultra Planning, Karpathy's Obsidian RAG, and Context Optimization

AI Video and Image Generation API Landscape 2026 — Pricing, Models, and Platform Comparison

The Claude Ecosystem Explained — Chat, Cowork, and Code

Setting Up Grafana Cloud Observability for a FastAPI Application

Hybrid Image Search Dev Log #9 — OpenTelemetry Distributed Tracing, Grafana Cloud Integration, traced_span Helper

Google Veo 3.1 and the Video AI Background Removal Ecosystem

Claude Code Harness Anatomy #6 — Beyond Claude Code: A Retrospective on Building an Independent 7-Crate Harness

Claude Code Harness Anatomy #5 — MCP Services and the Plugin-Skill Extension Ecosystem

Claude Code Harness Anatomy #4 — Runtime Hooks: 26+ Events and CLAUDE.md 6-Stage Discovery

Claude Code Harness Anatomy #3 — The Design Philosophy of 42 Tools, from BashTool to AgentTool

Claude Code Harness Anatomy #2 — The Heart of the Conversation Loop: StreamingToolExecutor and 7 Continue Paths

Claude Code Harness Anatomy #1 — From Entry Point to Response: The Journey of a Single Request

Pylette: Analyzing a Python Color Palette Extraction Library

PopCon Dev Log #2 — Branding, README, Docker Debugging, and Retry Logic

MediaFloat: Anatomy of an Android Floating Media Control Overlay

Log-Blog Dev Log #6 — Bilingual Setup, CDP Reliability, Marketplace Migration

k-skill: A Korean-Specific Skill Collection for Claude Code

Hybrid Image Search Dev Log #8 — Tone/Angle S3 Migration, EC2 Deployment Fixes, Hex Color Extraction

Claude Code Plugin Marketplace: A Deep Dive

Claude Code Cache Bug Analysis: 7 Confirmed Bugs and Their Impact

TurboQuant, Plit, and Nano Banana 2 - From Local AI Quantization to AI Website Creation

Trading Agent Dev Log #8 — Multi-Factor Weighted Score System and Composite Score Migration

System Design Core Concepts - From Interview Prep to Production Architecture

PopCon Dev Log #1 - Building an AI Animated Emoji Generator

OpenClaw Launch and the Future of the AI App Ecosystem - Will 80% of Apps Disappear?

Log-Blog Dev Log #5 — Firecrawl Deep Docs Integration and Bilingual Blog

Hybrid Image Search Dev Log #7 — LLM Category Classification and S3 Migration

HarnessKit Dev Log #4 — Marketplace Stabilization and v0.3.0 Release

Don't Fix the Prompt, Fix the Harness — The 4-Axis Framework and Generator-Evaluator Architecture

Claude Code Source Code Leak — Agent Architecture Exposed Through an NPM Source Map Mistake

Animated Emoji Market Research — From Platform Specs to Open-Source Tools

AI Image Generation Ecosystem Analysis — Qwen-Image-Layered, Nano Banana 2, Veo 3.1, vLLM-Omni

The Excalidraw Diagram Skill — Teaching Coding Agents Visual Argumentation

How Stripe Ships 1,300 PRs a Week — Coding Agents and Adversarial Development

Honeycomb and Observability Fundamentals — Comparing Open Source Alternatives

Firecrawl — The Web Scraping Powerhouse for the AI Era

Claude Code Practical Guide 5 — 12 Hidden Settings You Should Enable

Claude Code Practical Guide 4 — auto-fix and the Self-Healing Workflow

Claude Code Learning Roadmap — From Official Docs to Korean Community Guides

Automating Observability with Honeycomb MCP

A New Paradigm for Building AI Agents — From Frameworks to SDK-First

4 Essential MCP Servers for Claude Code — Playwright to Firecrawl

2026 npm Supply Chain Attacks — axios, LiteLLM, and the Lessons Learned

12 Practical Uses for NotebookLM — A Complete Guide to Your Free AI Research Assistant

Trading Agent Dev Log #7 — DCF Valuation, Portfolio Risk Analysis, and the 6th Expert

Superpowers Follow-up — From 69k to 110k Stars, and What's Still Missing

Long-Running AI Agents and Harness Engineering in Practice

LiteParse and the End of the Framework Era — LlamaIndex's Strategic Pivot

Hybrid Image Search Dev Log #6 — S3 Image Storage Migration and Branding

Claude Code Practical Guide 3 — 27 Tips from 500 Hours of Use

Claude Code Automation Triple Play — Skills, Scheduling, and Dispatch

Vibe Coding Security Checklist — OWASP Top 10 and Automated Scanning

Trading Agent Dev Log #6 — Deeper Analysis and Major Frontend Expansion

The LLM Trading Agent Ecosystem — TradingAgents, StockBench, FinRL-DeepSeek

The CLIP Ecosystem — From OpenAI to MetaCLIP2 and MobileCLIP2

Log-Blog Dev Log #4 — Preparing for the Official Marketplace

Hybrid Image Search Dev Log #5 — Inpaint UX, EC2 Dev Server, Stability

HarnessKit Dev Log #3 — Plugin Trigger Fixes and Marketplace Recommendation System

Google AI Studio Full-Stack Vibe Coding — Antigravity Agent and Firebase Integration

Get Shit Done — A Meta-Prompting System That Solves Context Rot

Gemini Video Embedding — A New Paradigm for Multimodal Search

Designing AI Apps for Production — Deterministic Fallback, HITL, and Evaluation Stack

Consistent UI with Claude Code and Figma — Analyzing Figma Community Resources

Claude Computer Use — An AI That Controls Your Mouse and Keyboard

Two Faces of AI Creative — Giantstep's Hybrid VFX Pipeline and Val Kilmer's Final Film

Spotify Data Engineering — Practitioner Meetup Recap and Platform Evolution in 2026

oh-my-opencode — A Model-Agnostic Agent Orchestrator

Log-Blog Dev Log #3 — From Skill to Plugin

Hybrid Image Search Dev Log #4 — Router Extraction, Terraform Dev Server, Inpaint Editor

Claude Code Practical Guide Part 2 — 9 New Features from the Last Two Months

tmux vs cmux — Battle-Tested Terminal Multiplexer vs the AI Agent Terminal

tmux Masterclass — Everything You Need to Know, Including AI Agent Integration

Trading Agent Dev Log #5 — Backend Stabilization and Data Pipeline Improvements

The Subagent Era Has Arrived — GPT 5.4 nano and Strategies for Context Rot

oh-my-claudecode (OMC) — Teams-First Multi-Agent Orchestration for Claude Code

MEGA Code — AI Coding Infrastructure That Evolves from Session Logs

Log-Blog Dev Log #2 — Unified Skill Flow and --since-last-run Tracking

Hybrid Image Search Dev Log #3 — Async Parallelization, Prompt Quality, and Structural Refactoring

Hybrid Image Search Dev Log #2 — Auto-Injection Visualization, User Isolation, and Async Parallel Generation

HarnessKit Dev Log #2 — Going Marketplace-First and Building v2a/v2b

HarnessKit Dev Log #1 — Designing and Building an Adaptive Harness Plugin for Zero-Based Vibe Coders

gstack — YC CEO Garry Tan's Claude Code Virtual Engineering Team

Context7 — A Deep Dive into the Platform That Injects Up-to-Date Docs into LLMs

Claude Code Plugin Marketplaces Compared — Where to Find Them and How to Choose

Claude Code Harness Plugins Compared — claude-code-harness vs. claude-harness

Harness Engineering #2 — Building Real Harnesses with Antigravity

Claude Skills V2 — A Skill System Evolved with Benchmarking and Automated Evaluation

Claude Code Practical Guide — Context Management to Workflow Patterns

Stock Trading Agent Dev Log #4 — DART Integration, Signal Critic, Real-time Dashboard

Stock Trading Agent Dev Log #3 — TradingAgents: A 30K-Star Multi-Agent Trading Firm Simulator

Replit Agent 4 — From Coding Agent to Creative Collaboration Platform

MegaUpskill Dev Log — Automating i18n Audits and Translation Gap-Filling

log-blog Dev Log — Extracting Dev Logs from Claude Code Sessions

Infratice — A Problem-Based DevOps Troubleshooting Platform Built on Real Incident Logs

Hybrid Image Search Dev Log — Implementing the Google OAuth Login Wall

From Neural Style Transfer to Virtual Humans — Three Approaches to AI Image Generation

Vibe Coding Fundamentals — The Core Principles in 33 Minutes

stock-analysis-agent — Automating Institutional-Grade Stock Research with Claude Code

recon — A tmux Dashboard for Managing Claude Code Agents Like Tamagotchis

Google Pomelli — AI Marketing Tool That Builds On-Brand Content from a URL

cmux — A macOS-Native Terminal Designed for the AI Agent Era

Claude In-Chat Interactive Visuals — When a Conversation Becomes a Dashboard

Claude for Chrome — Anthropic's Strategy to Embed AI Into the Browser

Claude Code Remote Control — Pick Up Your Coding Session From Any Device

AI Frontier Podcast: Three Episodes — AlphaGo at 10, the RL Era, and Agentic Workflows

page-agent — Alibaba's Open-Source Tool That Turns Any Web Page Into an AI-Native App With One Line of Code

GPT-5.4 Prompt Guide Essentials — Lock Down the Contract Before Tuning Reasoning

geo-seo-claude — Automating GEO for the AI Search Era with Claude Code

Claude Code /btw — Ask Side Questions Without Breaking Your Flow

Three AI Coding Agent Extension Frameworks Compared — bkit-codex, oh-my-codex, and Superpowers

The Evolution of AI Coding Agent Session Management — agentsview vs agf

opencode serve/web — Control Your Dev PC Remotely From Your Phone

ncdu — The TUI Tool for Quickly Understanding Linux Disk Usage

Gemini Embedding 2 — Google's First Native Multimodal Embedding Model

ClaudeTuner — Real-Time Claude Usage Tracking and Plan Optimization

VSCode + code-server OAuth Failures — The code-oss:// Scheme Problem Explained

Ralph Loop — The Agent Loop Pattern Where AI Tests and Fixes Itself

Harness — From General-Purpose AI to Dedicated Team Member

Google Code Wiki — Let AI Write Your Codebase Documentation

Google Antigravity IDE Deep Dive — A New Player in the AI IDE Wars

Claude Code 2026 — Statusline Update and the Multi-Environment AI Coding Ecosystem

Building High-Quality Presentations with Gemini + NotebookLM — From Research to Slides

Google Antigravity IDE — The New Contender in the AI IDE War

Building a Stock Trading Agent #2 — Expert Agent Team and KOSPI200 Data Struggles

Superpowers: Injecting Engineering Discipline into Claude Code

Nano Banana 2 Deep Dive — Google's Latest Image Generation Model

Claude Code's Three Core Concepts — Skills, Subagents, and Commands

Claude Code Token Optimization — Practical Strategies to Cut Costs by 80%

Claude Code Agent Teams — A New Paradigm for Multi-Agent Collaboration

Publishing a VS Code Extension — The Complete vsce Workflow

KIS Developers — Korea Investment & Securities Open API and MCP Trading

Kintsugi — SonarSource's ADE Built for Claude Code

vscode-mcp-server — Exposing VS Code's Editor Capabilities to LLMs via MCP

The VS Code Extension Ecosystem in 2026: From Webview UI Toolkit's End to AI Extensions

KIS Trading Agent — LLM Stock Trading Architecture with MCP

Gemini 3 — Function Calling, Structured Outputs, and Code Execution New Features

Claude Code Hooks — Deterministic Control Over Agent Behavior

AWS ECS Service Operations and CLI Credential Setup

VS Code Extension Development: Implementing OAuth with URI Handlers

Running Python + Node.js Multi-Service Apps with PM2 — A Complete ecosystem.config.js Guide

Observability vs Monitoring: Honeycomb vs Grafana

Gemini 3 Flash Preview Bug: Infinite Reasoning Loop and Internal Logic Leak

VS Code Extension Development — Remote Architecture, Core APIs, and Secret Security

Monolithic vs Microservices — How to Choose the Right Architecture

Alembic — Database Migration with SQLAlchemy

Gemini 3 Image Generation API + Mermaid.js Diagram Syntax

Tech Log: 2026-02-19

log-blog — Turning Browser History into Blog Posts Automatically

Hugo Theme Comparison & GitHub Pages Setup Guide

Archon — The Command Center for AI Coding Assistants
