Practical AI GenAI risks and global adoption
Aug 27, 2025
Rick Kobayashi, Co-founder and CEO of Citadel AI, and Kenny Song, Co-founder and CTO, previously with Google Brain, dive into the world of generative AI. They discuss Japan's unique approach to AI adoption, contrasting it with Western regulatory frameworks. The conversation addresses the security challenges of AI systems, including hallucinations and prompt injections, while exploring risk management in finance. They also consider the implications of rapid advancements like ChatGPT-5 and the exciting opportunities that AI brings to society.
AI Snips
Chapters
Transcript
Episode notes
Japan: Adoption Over Development
- Japan lags in foundation-model development but leads in everyday GenAI adoption and usage.
- Cultural familiarity with friendly robots lowers barriers for chatbots and consumer tools.
Soft Regulation, Hard Reputation Risks
- Japan uses a 'soft approach' with guidance rather than strict AI regulation.
- Businesses there worry more about reputational risk than purely technical security risk.
Prepare POCs Before Production
- Test and govern LLMs before moving proofs of concept into production.
- Mitigate hallucinations, toxicity, and prompt injection as part of deployment readiness.