akari.log

Tags /

ai

21 posts

Local LLMLonger Thinking Logs, Better Answers? 18 Runs with Qwen3 and Muse Glimmer
JA
AIUnderstanding the AI Industry Through Fate (2026 Edition)
JA
Local LLMChoosing a Local LLM Through Fate (2026 Edition)
JA
SecurityCloudflare OS Lets an AI Agent Run Wild Without Letting It Leak
JA
Local LLMRunning Cloudflare OS on a Local LLM, and Why One Tic-Tac-Toe Took Five Rounds
JA
AIDeveloping with Multiple Models? Make Sure You Design the Handoff
JA
ToolsDoes Claude Code Need Sleep? Inside the Unreleased Auto-dream Feature
JA
ToolsZero Trust for AI Agents? Google Workspace CLI's Design Philosophy
JA
ToolsHow to Stop Claude Code Skills from Drifting with Per-Step Constraint Design
JA
ToolsI've organised the Claude Code commands, including some hidden ones.
JA
Tools【GAS x Gemini】Prompt to Create an In-house Web App with UI/UX Awareness in 15 Minutes
JA
DevAI Auto-Translation, On by Default. What a Japanese Dev Platform Learnt in Eight Hours
JA
AIIs JSON Outdated? The Reasons Why the New LLM-Era Format "TOON" Saves Tokens
JA
ToolsIncrease my familiarity with BASE64.
JA
SecurityIn 2025, AI regulations were established in four major global regions.
Toolsdraw.io vs Mermaid vs PlantUML: How Engineers Actually Choose Diagramming Tools
JA
AILLMs Learn from "Pseudoscientific Papers" Too - Quality Control for AI Developers
JA
SecurityAI Chatbot Developers: What's the "Other Safety" We Should Be Thinking About Now? User Protection.
JA
ToolsGoogle Opal is not a “degraded Dify”. Its strategic positioning and optimal utilisation methods revealed through actual use
JA
AIWhen Your CEO Says 'Let's Use AI': A Technology Selection Survival Guide
JA
AIThe Era of Choosing RAG — Learning Cognitive Load and Architecture Design from GPT-5’s Failures
JA