Arthur Jiang

Software Engineer | Linux Enthusiast | High School Sophomore

About Me

I'm Arthur Jiang, a software engineer and Linux enthusiast currently studying as a sophomore at Emerald High School.

I have a deep passion for building tools that automate the mundane and exploring the depths of operating systems. When I'm not conducting research on LLMs or building window managers in the browser, you can find me customizing my Arch Linux setup or making boba.

Quick Stats

Dublin, CA
Class of 2027
Python JavaScript Linux Playwright AI/ML

Experience

Barista
Qtea Dublin
June 2025 - Present

Brewing joy, one boba tea at a time. Handling customer service and drink preparation in a fast-paced environment.

AI Research Intern
Algoverse
Q1 2025 - Q2 2025

Conducted research on Bayesian reasoning performance in Large Language Models (LLMs) in the context of bandit simulation problems.

Student
Emerald High School
August 2024 - Present

Currently a 10th-grade student focusing on Computer Science and Mathematics.

Selected Works

Agent SURF

Python Playwright AppleScript

An AI-backed automation framework for completing repetitive tasks like web scraping and computer actions. 🏆 3rd Place at ModelMinds Hackathon

SuperVision

Python APIs AI

AI-powered calendar tool that automatically schedules events and reminders based on images captured by the user. 🏆 1st Place at EHS Hackathon

Browserdesk.js

Vanilla JS HTML5

A vanilla JavaScript library for creating a full desktop-like OS experience entirely within the browser window.

Rabbitt

Node.js Playwright

An attempt at reverse engineering Rabbit's LAM (Large Action Model). The predecessor to Agent SURF.

DuckOS

Web Proxy

A simple OS-like interface for the browser, focused on bypassing internet censorship in schools. Acquired in 2023.

Kindler

ES5 JS Kindle

A niche project providing basic utilities and games designed specifically for the Kindle Paperwhite offline environment.

Research

✅ Accepted ORIGen 2025 EthicalLLMs - RANLP 2025

TextBandit: Evaluating Probabilistic Reasoning in LLMs Through Language-Only Decision Tasks

Authors: Arjun Damerla, Jimin Lim, Yanxi Jiang, Nam Le

Venue: Montreal, Canada (October 2025)

This research paper evaluates probabilistic reasoning capabilities in Large Language Models through language-only decision tasks, specifically focusing on bandit simulation problems. The work explores how LLMs perform Bayesian reasoning in contextual scenarios without numerical computation.

View on OpenReview

Certifications

Section Leader/Mentor

Stanford Code in Place

June 2025

View Certificate

AI Hackathon - 3rd Place

ModelMinds

Jan 2025

View Certificate

Intermediate Problem Solving

HackerRank

Jan 2025

View Certificate

Responsive Web Design

FreeCodeCamp

May 2023

View Certificate

Get In Touch

Have a project in mind, want to discuss research, or just talk Linux?

Say Hello