All Posts

Three principles for navigating the AI research firehose: prioritizing information sources (blogs over papers for frontier insights), building domain-specific harnesses instead of chasing hype, and constructing a personal research infrastructure with unified memory and automated pipelines.

From adventure and exploration in the first half to stability and reflection in the second half - sharing thoughts on compound interest of time, recording in the AI era, and living a fulfilling life within a smaller radius.

Two production-grade systems for real research scenarios: a paywall-crossing paper harvester and a self-iterating AI Scientist, demonstrating how Skills and Subagents upgrade LLMs into research infrastructure.

Drawing on Wittgenstein's philosophy, a recent paper argues that our existing language might be the fundamental bottleneck.

From interview reflections and Coffee Chats to AI-assisted writing and a digital-nomad experiment in Bali, this essay explores how to build an inner anchor in an age of labels, algorithms, and uncertainty.

From Web 3.0 to Bitcoin breaking $100K, from speculators to true believers - exploring the technical potential of cryptocurrency, its future direction, and the possibility of a decentralized society in the AGI era.

Two weeks volunteering at a lakeside cafe in Yunnan, and reflections on freedom, labor, rural life, and how privilege shapes our sense of possibility.

From the struggles and breakthroughs during my research internship at Peking University, to self-exploration after securing graduate admission - documenting growth and reflections in research, reading, and life planning in 2024.

Introduce a number of methods for optimizing the output of large language models and reducing the probability of irrelevant or incorrect responses.

Introduce a number of methods for optimizing the output of large language models and reducing the probability of irrelevant or incorrect responses.