Paper reading: AI is better at experiments—but does that mean better research taste?
Reading TasteVal through the distinction between doing research efficiently, recognizing its value, and exercising the judgment needed to evaluate both.
Oct 12, 2026
LegalWorld: A Life-Cycle Interactive Environment for Legal Agents
Collaborative research / third author: primarily responsible for frontend development and interaction design, with contributions to human evaluation, system integration, and project presentation.
Jun 17, 2026
Paper reading: LLMs CAN GET 'BRAIN ROT'! - Research on cognitive decline in large language models
Research from the University of Texas at Austin, Purdue University and other institutions proposed and verified the LLM Brain Rot hypothesis, and found that continued exposure to spam online text will lead to cognitive decline in large language models, including changes in reasoning ability, long text understanding, security and personality traits.
Oct 31, 2025
Paper Reading: How Prompt Word Politeness Affects LLM Accuracy: Mind Your Tone Paper Analysis
Penn State University research found that using rude prompt words can actually improve the accuracy of ChatGPT-4o, challenging people's traditional understanding of politeness in AI interactions
Oct 17, 2025