In Berkeley, California. Exploring AI products, and researching neural-network-based parameter estimation in Anne Collins' lab.
Built an AI-visibility action system for local businesses: it asks 10 leakage-checked discovery questions through OpenAI and Gemini, preserves the citation evidence, then prepares customer-authorized website, Yelp and directory actions.
Evaluated a live AI career agent across onboarding, interview, resume and decision workflows — turning trust gaps and UX friction into implementation-ready product recommendations.
A real-time AI companion that detects livestream highlights, follows caption context and reacts through a selectable persona.
Twelve situational questions become a mix of fictional characters through LLM simulation and Bayesian inference.
Welldify · Supported LLM monitoring across 66,000 labeled sentences and built a semi-automated workflow that shipped 30+ psychoeducation carousel sets.
View work ↗Artificial neural networks for parameter estimation and model identification in computational cognitive models — asking when ML systems can replace expensive Bayesian inference, and where they shouldn't.
Atypical Functional Network Trajectories in Autism Spectrum Disorder — invited revision at PNAS, 2026. Deployed neuroimaging pipelines on HKU's HPC (a first for the lab), processed ABIDE-I/II and ADHD-200 datasets, and found that ASD subjects show elevated similarity to normative atlases in later life.
The pyramid says you need food, shelter, money, love before you can do spiritual work. But a lot of the best art came from people whose base needs were not met — and arguably because they weren't.
The real user task is "I'm going to X, but I also want to check out Y" — a near-universal trip pattern that today's maps still don't make easy.
Hardware: a foldable, Switch-sized core — a 12-key octave plus collapsible drum pads. Software: an AI music agent — hum a melody or describe what you want, and it arranges and lays it onto your tracks.