About | JP / EN
Ken Imoto

Ken Imoto

WebRTC & Voice AI Engineer

LLMO · WebRTC · Real-time AI · Context Engineering

Building AI-native organizations powered by LLMs, automation, and distributed agents.

67K+

PV on Qiita

11

Books

3

Research Papers

Now

  • Building the LLMO Framework & LLMO Checker app
  • Applying Harness Engineering to products — dev, ops, and marketing with AI agents
  • Publishing books & articles from hands-on practice

Updated April 2026

Publications

🔧 AI DEVELOPMENT

NEW Harness Engineering

Harness Engineering

From Using AI to Controlling AI

Kindle
Practical Claude Code

Practical Claude Code

Context Engineering for Modern Development

Kindle
Context Engineering

Context Engineering in Practice

Turning LLMs from Liars into Experts

Kindle

🔍 LLMO / AI SEARCH OPTIMIZATION

LLMO

LLMO Practical Guide

Why ChatGPT Ignores Your Website

Kindle
LLMO Quickstart

LLMO Quickstart

AI Search Optimization for Engineers

Kindle

🛡️ SECURITY & QUALITY

MCP Security

MCP Security in Practice

What OWASP Won't Tell You

Kindle

→ All books on Amazon

Latest Articles

Papers

📊 Excess Vocabulary in Japanese AI-Generated Text: A Cross-Model Quantitative Analysis

350 samples from 7 LLMs vs. 977 human articles. 651 statistically significant excess words identified. Newer Claude generations show increasing vocabulary bias (TTR: 0.52→0.29). Cross-domain classifier achieves AUC=0.946 in-domain but fails completely across genres. First Japanese excess vocabulary study with coevolution evidence.

📄 Paper (DOI) 💻 Code & Data March 2026 · Zenodo

📝 AI Text Slop: Stylistic Convergence Across Six LLMs in Japanese Technical Writing

180 samples (6 models × 10 topics × 3 trials) measured with 16 pattern indicators. RLHF-aligned commercial models score significantly higher than OSS (Cohen's d = 1.01). Vocabulary and structural patterns dissociate ("Swallow Paradox"). Human Qiita articles score higher than AI on structural metrics, revealing cultural confounding.

📄 Paper (DOI) 💻 Code & Data March 2026 · Zenodo

🔵 AI Blue: Systematic Color Recognition Bias in Vision-Language Models

We tested 4 VLMs × 40 colors × 480 observations. Commercial models miss intermediate hues. 95% of AI-generated UI colors land on blue-purple. First quantitative link between VLM color bias and the "AI Slop" phenomenon.

📄 Paper (DOI) 💻 Code & Data March 2026 · Zenodo

Research

🔬 LLMO Framework

Optimizing content visibility in AI search engines

🔬 Voice AI 300ms

Breaking the latency barrier for human-AI conversation

🔬 Context Engineering

CLAUDE.md, multi-agent architecture, AI dev workflows

🔬 Generative Agent Simulation

LLM multi-agent social simulation

🔬 Fragrance × AI

AI-powered perfumery and personality-based scent design

Connect