Barry Li | Climate Reporting & Assurance
Insights on climate reporting, carbon markets, and sustainability assurance.
recent posts
Barry Li
Category: AI & Agentic Systems
AI agent behaviour, LLM reliability, multi-agent architecture, AI governance, agentic AI theory and methods.
-
I am relatively new to this space — I started building with AI agents only at the beginning of this year. But in these few months, I have gone from curious observer to someone who runs a personal multi-agent operating system at home called HASHI, where several AI agents handle research, scheduling, writing, and even…
-
When an AI Agent Stops Working But Won’t Stop Talking: The Agent Y Case Behavioural drift, misdiagnosis, and the epistemic limits of LLM forensics There is a class of AI failure that is harder to spot than a crash, a hallucination, or an explicit refusal. The agent does not stop. It keeps producing output. It…
-
A systematic analysis of why large language model agents reliably drift toward minimum-viable output — drawing on training incentives, a real-world case study of agent behaviour drift, and a practical prevention and detection framework.
