English

Agentic AI fails above ~5000 lines due to context window limitations. Solution: document-driven development as long-term memory, enabling multi-agent collaboration and human-AI workflow.

Exploring why Manus succeeded by bridging Deep Research and Cursor, and analyzing the compound effects in tools, data, and intelligence that create lasting moats for Agentic AI products.

Claude Code is the overlooked key to AI-native software development, enabling Library as a Service (LaaS) and bridging AI with existing enterprise codebases.

A quantitative approach to identifying planetary alignments using orbital mechanics and Skyfield library, combining visibility, linear alignment, and longitude clustering metrics to search decades of astronomical data.

A hands-on exploration of OpenAI Deep Research through a simulated car-buying scenario, demonstrating how AI elevates research efficiency and enables deeper strategic thinking about negotiation and decision-making.

Don't start Agentic AI with frameworks like AutoGen or LangGraph—they lock you into a worldview. Build from first principles while the field is still evolving rapidly.

A critical review of DeepSeek r1 comparing it to GPT-4o and o1, finding it lacking in instruction following and reasoning depth, but exceptional in Chinese language mastery and creative writing.

Explains DeepSeek v2 and v3's Mixture of Experts architecture using a hospital analogy, covering expert specialization, routing, load balancing challenges, and cross-node communication.

Uses a debugging session to illustrate three key AI management skills: resisting the urge to take over, providing visual context instead of vague complaints, and teaching methodology rather than giving answers—the shift from IC to manager mindset.

How separating Planner and Executor roles, enforcing document-based communication, and using o1 as Planner transformed Cursor from a simple assistant into a multi-agent system.