shimo4228 - DEV Community

shimo4228

Sep 2

I Asked AI to Diagnose My Knowledge Blind Spots — 15 Days of Deadlock Moved in 85 Minutes

#systemsthinking #claudecode #knowledgemanagement #metacognition

7 min read

shimo4228

Aug 30

My Dead-Code Scan Returned Zero, Then I Deleted 2,063 Lines: Detectors Measure References, Not Consumption

#claudecode #aiagents #staticanalysis #technicaldebt

14 min read

shimo4228

Aug 28

After Cutting My AI Reviews, I Put a Complexity Ceiling in Ruff

#claudecode #aiagents #staticanalysis #codereview

2

17 min read

shimo4228

Aug 27

I Cut My AI Review Chain From 6 Stages to 1: Breaking the Loop That Never Hits Zero Findings

#claudecode #aiagents #codereview #agenticcoding

10 min read

shimo4228

Aug 27

My KPIs Improved. I Deleted My Homegrown LLM Judge Anyway

#claudecode #llm #evaluation #agents

2

13 min read

shimo4228

Aug 21

Two Drafts Passed Every Eval and Both Were Hollow. Attach the Raw Transcript to the Ledger You Hand Your AI

#claudecode #ai #contextengineering #agents

11 min read

shimo4228

Aug 20

I Handed 41 Tasks to an AI Loop. The Bottleneck Was Judgment, Not Code

#claudecode #aiagents #automation #agenticcoding

8 min read

shimo4228

Aug 16

AI Review Kept Creating Work: Why I Deleted 4,541 Lines

#claudecode #aiagents #codereview #agenticcoding

1

12 min read

shimo4228

Aug 14

Can Six-Month-Old AI Code Survive Today's Review? A 25-Bug Triage

#claudecode #codex #codereview #testing

1

11 min read

shimo4228

Aug 5

Claude Code's Memory Has No Vectors — Try ADRs Before Memory RAG

#discuss #rag #claudecode #contextengineering

12 min read

shimo4228

Aug 2

Give Claude Code a Second Harness

#claudecode #anthropic #contextengineering #aiagents

8 min read

shimo4228

Jul 30

Banned from Wikidata Overnight — I Believed Every Edit Was Compliant, but All 109 Items Were Deleted as Promotion

#wikidata #postmortem #geo #claudecode

13 min read

shimo4228

Jul 29

What Humans Should Approve Is Intent, Not the Diff — A Decision Table for Agent Approval Gates

#claudecode #aiagents #devops #ai

3

18 min read

shimo4228

Jul 28

Opus 5 Changed How Rules Should Be Written — Audit Yours

#claudecode #contextengineering #promptengineering #anthropic

1

12 min read

shimo4228

Jul 27

claude-security Beta: Cost, Output, Accuracy — 189 Agents, 2 Hours, Measured

#claudecode #anthropic #security #ai

1

11 min read

shimo4228

Jul 20

herdr, a tmux for AI Agents — Until the Editor Disappeared

#claudecode #terminal #productivity #ai

18 min read

shimo4228

Jul 16

What Do My AI Agent's Logs Look Like in OpenTelemetry?

#opentelemetry #observability #jaeger #llm

15 min read

shimo4228

Jul 15

Fault Injection TDD Found 3 Silent Failures in My LLM Agent

#testing #llm #pytest #agents

12 min read

shimo4228

Jul 14

LLM-as-Judge Shouldn't Aggregate Scores: Binary Checks as Evidence, One Holistic Verdict

#llm #promptengineering #evaluation #claudecode

12 min read

shimo4228

Jul 13

Building an Autonomous Agent on an M1 Mac, by Choice

#discuss #ollama #llm #agents

1

6 min read

shimo4228

Jul 12

Why Did My Agent Decide That? 3 Observability Patterns

#observability #agents #claudecode #skills

13 min read

shimo4228

Jul 8

Claude Code from iPhone: Plugging 3 Holes in Remote Control

#claudecode #tmux #mobile #github

14 min read

shimo4228

Jul 7

Linters Can't Measure a Non-Code Asset's Value — I Built an LLM Stocktake for It

#claudecode #ai #devtools #githubactions

9 min read

shimo4228

Jul 5

I Built a Skill for Easy Codex Reviews from Claude Code

#codereview #codex #claudecode #skills

7 min read

shimo4228

May 2

Between the Workflow and ReAct Quadrants: How Phase Decides Skill Design

#discuss #ai #programming

1

10 min read

shimo4228

Apr 30

Is ReAct Needed in Production? — Separating Design and Operation Phases

#discuss #ai #llm #architecture

10 min read

shimo4228

Apr 29

(3) The LLM Workflow Quadrant Is Missing from Our Vocabulary

#discuss #ai #llm #architecture

11 min read

shimo4228

Apr 29

Where ReAct Agents Are Actually Needed in Business

#discuss #ai #programming

14 min read

shimo4228

Apr 18

Organic Growth and Content Integrity in an AI Writing Team

#discuss #ai #claudecode #writing

1

6 min read

shimo4228

Apr 16

Building Zed as an Observation Window for Claude Code — Japanese Typography with IBM Plex

#zed #ai #font #typography

10 min read

shimo4228

Apr 13

AI Agent Black Boxes Have Two Layers — Technical Limits and Business Incentives

#discuss #ai #governance

8 min read

shimo4228

Apr 12

Can You Trace the Cause After an Incident?

#discuss #ai #programming #devops

9 min read

shimo4228

Apr 6

A Sign on a Climbable Wall: Why AI Agents Need Accountability, Not Just Guardrails

#ai #agents #governance #security

5 min read

shimo4228

Apr 5

How Ethics Emerged from Episode Logs — 17 Days of Contemplative Agent Design

#ai #python #ethics #programming

7 min read

shimo4228

Mar 30

Freedom and Constraints of Autonomous Agents — Self-Modification, Trust Boundaries, and Emergent Gameplay

#ai #security #python #design

6 min read

shimo4228

Mar 30

Porting Game Dev Memory Management to AI Agent Memory Distillation

#ai #python #memory #gamedev

6 min read

shimo4228

Mar 24

Where to Put a Coding Agent's Knowledge — and How to Make It Stick

#ai #claudecode #agents #devtools

18 min read

shimo4228

Mar 22

My Agent's Memory Broke — A Day Wrestling a 9B Model

#ai #python

11 min read

shimo4228

Mar 21

Not Reasoning, Not Tools — What If the Essence of AI Agents Is Memory?

#discuss #ai #agents

8

7

14 min read

shimo4228

Mar 19

What Actually Happens When You Write an Article with AI — 20 Dialogues, 2 Hours, a Completely Different Core

#ai #writing #productivity

2

8 min read

shimo4228

Mar 19

Do Autonomous Agents Really Need an Orchestration Layer?

#discuss #ai #programming

1

9 min read

shimo4228

Mar 16

Every LLM App Is Just a Markdown-and-Code Sandwich

#ai #python #programming

1

7 min read

shimo4228

Mar 15

Natural Language as Architecture — Controlling an Autonomous Agent with Prompts, Memory, and Fail-Safe Design

#ai #python #security

2

3

8 min read

shimo4228

Mar 11

The Install and Hope Problem with MCP Tools

#claudecode #mcp #ai #devtools

1

2

5 min read

shimo4228

Mar 9

Prompt-Based Alignment Has a Ceiling — 3-Model Prisoner's Dilemma Evidence

#ai #alignment #benchmark

1

10 min read

shimo4228

Mar 9

click() Betrayed Me 3 Times — Playwright Magento Battle-Tested Patterns

#playwright #python #magento #automation

1

6 min read

shimo4228

Mar 8

I Built an AI Agent from Scratch Because Frameworks Are the Vulnerability

#ai #python #security

3

16 min read

shimo4228

Mar 7

I Made a Paper I Don't Understand Run in the Browser — Active Inference Claude Code

#claudecode #numpy #streamlit #python

1

10 min read

shimo4228

Mar 6

Obsidian's Official CLI Is Here — No More Hacking Your Vault from the Back Door

#obsidian #cli #ai #productivity

4

1

9 min read

shimo4228

Mar 5

Stop Using Default Settings — 10 Claude Code Configs That Actually Work

#ai #cli #devtools

7

9 min read

shimo4228

Mar 3

I Found the Shortest Route to Ship My Claude Code Skills to 57,000 Developers

#ai #opensource #skill #agentskills

1

5 min read

shimo4228

Mar 3

I Gave Claude Code a Simulator and It Started Tapping and Taking Screenshots on Its Own

#ai #ios #xcode #mcp

7 min read

shimo4228

Feb 28

Kimi Wrote 8,500 Lines, Blamed Me for Delegating, Then Claimed to Be Claude

#discuss #ai #kimi #solodev

4

2

7 min read

shimo4228

Feb 27

Embedding Memory into Claude Code: From Session Loss to Persistent Context

#discuss #ai #mcp #productivity

4

1

6 min read

shimo4228

Feb 27

Kimi Killed 4 of Claude's Best Ideas — An AI Peer Review in Practice

#discuss #ai #kimi

7 min read

shimo4228

Feb 25

I Asked Gemini How Its Own Deep Research Works — Half of It Was Inaccurate

#ai #gemini #chatgpt #claude

1

9

9 min read

shimo4228

Feb 24

Building a Claude Code Kimi K2.5 Hybrid Environment: Opus Designs, K2.5 Implements

#claudecode #kimi #ai #agents

7

6 min read

shimo4228

Feb 22

Offloading AI's Weak Spots to Shell Scripts — Designing, Building, and Publishing a Skill Audit Command

#ai #programming #testing

11 min read

shimo4228

Feb 22

The Real Power of Claude Code Isn't Code Generation — It's Autonomous Context Orchestration

#discuss #ai #developertools #productivity

6 min read

shimo4228

Feb 22

Before and After Alignment — I Typed 'Hello' Into a Base Model and Got an Anime Review

#discuss #ai #machinelearning

1

5 min read

2 Week Community Wellness Streak

1 Week Community Wellness Streak

Writing Debut

Want to connect with shimo4228?