Barry Li | Climate Reporting & Assurance
Insights on climate reporting, carbon markets, and sustainability assurance.
Category: AI & Agentic Systems
AI agent behaviour, LLM reliability, multi-agent architecture, AI governance, agentic AI theory and methods.
-
If you’re a CIO or CTO shaping your 2026 AI strategy, here’s the uncomfortable question I want you to sit with: Are the productivity tools your organisation actually runs on built for human-AI collaboration… or only for human-to-human work? Because almost everything still in use today was designed before 2023. And that creates a massive,…
-
The biggest highlight for me about OpenClaw was its elegant memory layer — specifically the soul.md and user.md design that gives AI agents genuine personality and real-world engagement. That simplicity stuck with me. A flat file. A few lines of prose. And suddenly, the agent felt like someone rather than something. It made me ask…
-
Here’s a hard truth in 2026: One of the world’s most sophisticated organizations — with elite talent and deep resources — had a critical vulnerability sitting in its flagship internal AI platform for over two years. An external autonomous AI agent found it in under two hours. In late February 2026, CodeWall pointed their offensive…
-
I used to think Claude was untouchable. It wrote beautiful code, had the best common sense, and felt genuinely human. For creative work and complex agentic tasks, nothing came close. When I started building HASHI — my personal multi-agent AI system — Claude was the backbone. Every major agent ran on it. Every complex workflow…
-
Everyone in the AI space talks about hallucination — the tendency for language models to fabricate facts with unshakeable confidence. It is a well-documented problem, widely discussed, and increasingly mitigated through better training and retrieval-augmented architectures. But there is a second failure mode that I believe is far more dangerous in practice, and I have…
-
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.
