灯里/iku

I'm a curious person who really enjoys AI. I write for fun as a personal hobby. Getting your reactions and follows really motivates me. The AI era has its challenges, but it's super fun!

JP Joined on Sep 19, 2025

Pronouns

She

Work

AI engineer

灯里/iku

Aug 17

Running Cloudflare OS on a Local LLM, and Why One Tic-Tac-Toe Took Five Rounds

#cloudflare #ollama #llm #ai

23 min read

Want to connect with 灯里/iku?

Create an account to connect with 灯里/iku. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

灯里/iku

Aug 16

From MPA to Islands, Sorting Out Frontend Architecture When There Is No Right Answer

#webdev #astro #frontend #architecture

12 min read

灯里/iku

Jul 23

Migrating to Astro, How I Built a Bilingual Static Blog

#astro #typescript #webdev #seo

12 min read

灯里/iku

Jul 20

Is TypeScript 7 Ready? 5x Faster, but Astro and Vue Say Wait

#typescript #astro #webdev #performance

9 min read

灯里/iku

May 10

Is Your Claude Code Safe From Base64? Inside 2026 AI Agent Attacks

#security #claudecode #base64 #aiagents

31 min read

灯里/iku

Mar 24

Does Claude Code Need Sleep? Inside the Unreleased Auto-dream Feature

#claude #claudecode #ai #productivity

9 min read

灯里/iku

Mar 7

Claude Code Ctrl+V Not Working on Windows? Fixes for Common Gotchas

#claudecode #windows #vscode #productivity

6 min read

灯里/iku

Mar 6

Zero Trust for AI Agents? Google Workspace CLI's Design Philosophy

#google #cli #ai #security

8 min read

灯里/iku

Feb 28

How to Stop Claude Code Skills from Drifting with Per-Step Constraint Design

#claudecode #claude #ai #promptengineering

10 min read

灯里/iku

Feb 14

I've organised the Claude Code commands, including some hidden ones.

#ai #cli #command #claude

15 min read

灯里/iku

Jan 24

【GAS x Gemini】Prompt to Create an In-house Web App with UI/UX Awareness in 15 Minutes

#gas #gemini #ai #webapp

12 min read

灯里/iku

Nov 27 '25

Is JSON Outdated? The Reasons Why the New LLM-Era Format "TOON" Saves Tokens

#ai #json #toon

5 min read

灯里/iku

Nov 16 '25

Increase my familiarity with BASE64.

#api #tutorial #ai #base64

12 min read

灯里/iku

Nov 12 '25

In 2025, AI regulations were established in four major global regions.

#ai #aigovernance #datasovereignty #techpolicy

8 min read

灯里/iku

Nov 6 '25

draw.io vs Mermaid vs PlantUML: How Engineers Actually Choose Diagramming Tools

#discuss #diagrams #documentation #ai

7 min read

灯里/iku

Oct 27 '25

RAG Architecture Design Theory and Conceptual Organization in the Age of AI Agents: 7 Patterns

#rag #llm #architecture #agents

20 min read

灯里/iku

Oct 25 '25

LLMs Learn from "Pseudoscientific Papers" Too - Quality Control for AI Developers

#ai #machinelearning #llm #developers

9 min read

灯里/iku

Oct 21 '25

Analyzing the Best Diagramming Tools for the LLM Age Based on Token Efficiency

#mermaid #tokenefficiency #devops #llm

7 min read

灯里/iku

Oct 17 '25

AI Chatbot Developers: What's the "Other Safety" We Should Be Thinking About Now? User Protection.

#ai #security #llm #safety

24 min read

灯里/iku

Oct 12 '25

Google Opal is not a “degraded Dify”. Its strategic positioning and optimal utilisation methods revealed through actual use

#ai #google #nocode #productivity

10 min read

灯里/iku

Oct 4 '25

"AI makes it cheaper, right?" - Is this happening in your country too?

3 min read

灯里/iku

Sep 30 '25

LLM Prompt Compression: Cut Token Costs by 50% with Logical Structure

#promptengineering #llm #costreduction #tokenoptimization

18 min read

灯里/iku

Sep 20 '25

When Your CEO Says 'Let's Use AI': A Technology Selection Survival Guide

#ai #career #management

13 min read

灯里/iku

Sep 19 '25

The Era of Choosing RAG — Learning Cognitive Load and Architecture Design from GPT-5’s Failures

#ai #rag #machinelearning #architecture

13 min read

DEV Community

灯里/iku

Badges

2 Week Community Wellness Streak

1 Week Community Wellness Streak

Writing Debut

Currently learning

Available for

Running Cloudflare OS on a Local LLM, and Why One Tic-Tac-Toe Took Five Rounds

Want to connect with 灯里/iku?

From MPA to Islands, Sorting Out Frontend Architecture When There Is No Right Answer

Migrating to Astro, How I Built a Bilingual Static Blog

Is TypeScript 7 Ready? 5x Faster, but Astro and Vue Say Wait

Is Your Claude Code Safe From Base64? Inside 2026 AI Agent Attacks

Does Claude Code Need Sleep? Inside the Unreleased Auto-dream Feature

Claude Code Ctrl+V Not Working on Windows? Fixes for Common Gotchas

Zero Trust for AI Agents? Google Workspace CLI's Design Philosophy

How to Stop Claude Code Skills from Drifting with Per-Step Constraint Design

I've organised the Claude Code commands, including some hidden ones.

【GAS x Gemini】Prompt to Create an In-house Web App with UI/UX Awareness in 15 Minutes

Is JSON Outdated? The Reasons Why the New LLM-Era Format "TOON" Saves Tokens

Increase my familiarity with BASE64.

In 2025, AI regulations were established in four major global regions.

draw.io vs Mermaid vs PlantUML: How Engineers Actually Choose Diagramming Tools

RAG Architecture Design Theory and Conceptual Organization in the Age of AI Agents: 7 Patterns

LLMs Learn from "Pseudoscientific Papers" Too - Quality Control for AI Developers

Analyzing the Best Diagramming Tools for the LLM Age Based on Token Efficiency

AI Chatbot Developers: What's the "Other Safety" We Should Be Thinking About Now? User Protection.

Google Opal is not a “degraded Dify”. Its strategic positioning and optimal utilisation methods revealed through actual use

"AI makes it cheaper, right?" - Is this happening in your country too?

LLM Prompt Compression: Cut Token Costs by 50% with Logical Structure

When Your CEO Says 'Let's Use AI': A Technology Selection Survival Guide

The Era of Choosing RAG — Learning Cognitive Load and Architecture Design from GPT-5’s Failures