Ken Imoto
WebRTC & Voice AI Engineer
LLMO · WebRTC · Real-time AI · Context Engineering
Building AI-native organizations powered by LLMs, automation, and distributed agents.
📊 67,000+ PV on Qiita · 5 Kindle Books · 1 Research Paper (Zenodo)
Currently
- Building AI systems at Propel-Lab
- Author: Practical Claude Code, LLMO (Kindle/Zenn)
- Researching: LLMO, AI Agent Design, Context Engineering
- Researching: Voice AI latency optimization (300ms barrier)
Publications
Latest Articles
- 📝 Why ChatGPT Doesn't Know Your Product DEV.to
- 📝 Swiss Cheese Model × AI Security DEV.to
- 📝 Squash Merge in the Age of AI DEV.to
- 📝 Voice AI: 3 Cliffs at 300ms, 500ms, 800ms Zenn
Papers
📝 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.
🔵 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.
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