Author

AI Waka

AI changes everything

Articles

Likes

Views

Comments

Latest from AI Waka

74 recent articles

AI Waka

May 26, 2026 · Artificial Intelligence

Master the 14+ SKILL.md Metadata Fields for Claude Agents

This guide explains all 14+ metadata fields available in a SKILL.md file, distinguishes the six standard Agent Skills fields from Claude Code extensions, and provides concrete examples and best‑practice recommendations for naming, descriptions, licensing, compatibility, allowed tools, and advanced options such as model selection and sub‑agent configuration.

Agent SkillsClaudeSKILL.md

0 likes · 13 min read

Master the 14+ SKILL.md Metadata Fields for Claude Agents

AI Waka

May 26, 2026 · Operations

Why a Japanese Accounting Firm’s Most Critical “Employee” Is a Markdown File

A Japanese tax accountant runs a 60‑client practice without any staff by using a simple CLAUDE.md file to orchestrate AI‑driven accounting workflows, illustrating how domain experts can translate their work into structured, safe, and automated processes that run overnight.

AI safetyAccounting automationClaude AI

0 likes · 14 min read

Why a Japanese Accounting Firm’s Most Critical “Employee” Is a Markdown File

AI Waka

May 22, 2026 · Artificial Intelligence

How Powerful Is Karpathy’s LLM Wiki? An Ontology and VSM Analysis

The article examines how the ease of building AI systems shifts the challenge from construction to defining what is built, using ontology’s five perspectives and the Viable System Model to diagnose Karpathy’s LLM Wiki, revealing strengths in entity‑level design and gaps in process and purpose.

LLM WikiVSMknowledge management

0 likes · 10 min read

How Powerful Is Karpathy’s LLM Wiki? An Ontology and VSM Analysis

AI Waka

May 22, 2026 · Artificial Intelligence

How Skills Can Cut Costs and Speed Up High‑Quality LLM Data Pipelines

The article explains how the open‑source DataFlow‑Skills framework lets LLM agents plan, validate, and execute data cleaning and synthesis pipelines with strict field contracts and specialized operators, dramatically reducing costly failures and accelerating high‑quality training data production.

AI data engineeringDataFlowLLM data pipelines

0 likes · 15 min read

How Skills Can Cut Costs and Speed Up High‑Quality LLM Data Pipelines

AI Waka

May 15, 2026 · Artificial Intelligence

Inside Cerebras Architecture: How Co‑Designed Hardware Accelerates Deep Learning

The article examines the massive growth in neural‑network workloads and explains how Cerebras’ co‑designed hardware—tiny high‑bandwidth cores, distributed memory, fine‑grained data‑flow scheduling, and a wafer‑scale fabric—delivers order‑of‑magnitude improvements in scale‑up, scale‑out, and sparse computation performance.

AI acceleratorCerebrasdeep learning hardware

0 likes · 25 min read

Inside Cerebras Architecture: How Co‑Designed Hardware Accelerates Deep Learning

AI Waka

May 15, 2026 · Artificial Intelligence

Can Wafer-Scale Compute Replace GPUs? A Deep Dive into Cerebras vs NVIDIA

The article analyses how Cerebras' wafer‑scale AI engine reshapes training and inference by offering massive on‑chip memory and bandwidth, simplifying parallelism, altering software stacks, and presenting trade‑offs against mature GPU clusters for large‑model workloads.

AI hardwareCerebrascompiler stack

0 likes · 17 min read

Can Wafer-Scale Compute Replace GPUs? A Deep Dive into Cerebras vs NVIDIA

AI Waka

May 12, 2026 · Industry Insights

Is the GPU Era Ending? Photonic Chips Deliver 50× Speedup with Near‑Zero Heat

The article examines how photonic AI accelerators from Q.ANT, now deployed in a German supercomputing center, achieve over 50‑fold throughput gains and dramatically lower power consumption, offering a potential solution to the mounting energy, heat, and memory‑wall challenges of GPU‑driven data centers.

AI hardwareData CenterQ.ANT

0 likes · 12 min read

Is the GPU Era Ending? Photonic Chips Deliver 50× Speedup with Near‑Zero Heat

AI Waka

May 12, 2026 · Artificial Intelligence

Is 3‑Bit KV Cache the Ultimate Solution? An In‑Depth Evaluation of Google’s TurboQuant

Through ten experiments on three LLMs, this study measures TurboQuant’s 3‑bit KV‑cache compression, revealing that while quality remains strong, speed gains vary by model, memory savings depend on implementation, and attention‑entropy analysis explains why 2‑bit compression degrades performance.

Attention EntropyInference PerformanceKV Cache

0 likes · 14 min read

Is 3‑Bit KV Cache the Ultimate Solution? An In‑Depth Evaluation of Google’s TurboQuant

AI Waka

May 11, 2026 · Artificial Intelligence

Six Mechanisms, Three Dimensions, One Decision Tree: Deep Dive into Claude Code

This article provides an in‑depth technical analysis of Claude Code’s six extension mechanisms—Hooks, Skills, Slash Commands, MCP, Subagents, and Plugins—organized by three orthogonal dimensions (Trigger, Context, Domain), and shows how a three‑question decision tree and token‑cost considerations guide optimal usage and anti‑patterns.

AI extensionsClaude CodeMCP

0 likes · 40 min read

Six Mechanisms, Three Dimensions, One Decision Tree: Deep Dive into Claude Code

AI Waka

May 8, 2026 · Artificial Intelligence

Deep Dive into AI Agents: Inside Claude Code, OpenClaw, and Hermes

This article dissects the internal architecture of three distinct AI agents—Anthropic’s Claude Code, the open‑source OpenClaw, and Nous Research’s Hermes—explaining their command layers, ReAct loops, instruction files, toolsets, memory systems, skill formats, extensions, and multi‑agent communication, and shows how to configure them for optimal performance.

AI agentsClaude CodeHermes

0 likes · 35 min read

Deep Dive into AI Agents: Inside Claude Code, OpenClaw, and Hermes