Geek AI Lab
RSS FeedExploring Artificial Intelligence, Machine Learning and Software Engineering through research notes, experiments and engineering practices.
This blog focuses on AI Agents, Large Language Models, Computer Vision, Model Optimization, Quantization, Compilers and Modern Computing Systems.
Welcome to my technical notebook, where I document ideas, implementations and lessons learned from building intelligent systems.
Recent Posts
DSec: The Infrastructure Layer Behind Scalable AI Agents
How DeepSeek's DSec platform provides scalable sandbox infrastructure for agentic AI training, reinforcement learning, and autonomous execution.
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
A technical introduction to Dream-RSI, a framework for recursive self-improvement that uses historical discovery trajectories as replay simulators to improve exploration strategies.
AI Agents Are Becoming the New Computing Paradigm
Why the next phase of AI is shifting from language generation toward reasoning, tool use, persistent execution, and autonomous systems.
AI Agents: Architecture, Reasoning, and Applications
A comprehensive introduction to AI agents, covering agent architecture, reasoning, planning, memory, tools, frameworks, applications, and future development.