Skip to content - Completed BlueDot AI Safety Fundamentals After completing BlueDot Impact AI Safety Fundamentals and receiving the certificate, I have a clearer view of agent safety evals, tool-use safety, and reliable AI infrastructure. AI · AI Safety · Reflection
- Distinguishing Saints from Sycophants and Schemers AI safety requires distinguishing saints from sycophants and schemers during training.
- MCP Is Infrastructure, Not the Ultimate AI Solution MCP standardizes how AI apps connect to tools, resources, prompts, and external systems. It is useful infrastructure for reducing integration glue, but it does not replace permissions, confirmations, logging, threat modeling, or tool-safety design. AI · AI Safety · Development · Tools
- Auto-Scrolling AI Chats: How to Read User Intent Auto-scroll in an AI chat is not just scrollTop. It needs intent signals, a follow/free state machine, handling for programmatic scroll events, virtualization, and mobile edge cases. Tools · Development · Reflection · AI
- How AI Coding Assistants Actually Improve Developer Efficiency Based on hands-on use of Copilot, Cursor, and Claude Code, this post separates where AI assistants help most, such as search, boilerplate, and error diagnosis, from where they still struggle, such as architecture and edge cases.
- Statsify Finance: Technical Breakdown A product and architecture walkthrough for Statsify Finance, covering its analysis, strategy, article, search, and finance-term pages, plus the Next.js, Tailwind, Ant Design, ECharts, MongoDB, and TypeScript stack behind it. Money · Development · Website building