CrossCurrents

On Systems, Incentives, and Machine Intelligence

If you're new here, I'd recommend visiting my about page to see what this site is about. I expect and welcome criticism from researchers, industry professionals, or anybody else, regardless of background or field of study. My goal is to be proven wrong, so that I can correct my assumptions.

My Best Work

Street-Legal Physical Adversarial Rim for License Plates

May 1, 2026

Flock Safety and similar companies have blanketed the country with license plate readers, tracking the movements of ordinary people without their consent. Inspired by a YouTube video, we built a practical countermeasure: a street-legal adversarial license plate rim that disrupts license plate readers without obscuring any part of the plate. Starting from scratch as two undergraduates with no lab support, we wrote and submitted a manuscript detailing our approach. Our work was accepted to the Security in Machine Learning Applications (SiMLA) 2026 workshop.

builds

AI Safety, Interpretability, and Insights from Biology

February 13, 2026

Will artificial superintelligence (ASI) ever be developed, and should we be seriously concerned about AI safety? I argue that the development of ASI is entirely possible, though likely not with our current large language model architectures. Safety is therefore a problem that needs to be solved, but we have sufficient time before the creation of an ASI to solidify our understanding of neural networks and objective function alignment. We need to use this time to build out interpretability research as a robust scientific discipline. I outline specific criticisms of the field from my perspective at the intersection of biology and computing, as well as actionable biology-inspired steps that could improve the scientific rigor of interpretability research and ensure we are fully prepared for ASI whenever the final breakthrough happens.

essays

Can Less Democracy Save Democracy?

August 15, 2025

Yep, I’ve finally lost it and decided to dip my toe into the radioactive cesspool of American politics. This is a terrible idea. Let’s do it.

essays

Latest

The Leaky AI Safety Pipeline
May 19, 2026
Many programs and fellowships exist in the AI safety community to get people interested in AI safety and build up their technical knowledge. However, there remains a substantial difficulty in getting from knowledgeable to a credible researcher with published and peer-reviewed output. I share my own guidelines to breaking out as an independent researcher and argue for an online resource that matches aspiring researchers with collaborators and presents guides from successful established researchers.
essays
ChatGPT-integrated Smartshell
September 24, 2023
I recently started playing with the idea of a “smart” command-line shell integrated with ChatGPT and implemented in Python. The code for my rudimentary implementation is freely available here, and should be simple enough to install and run on a Linux system.
builds
XBee Protocol Design (from scratch!)
August 28, 2023
This post was entirely AI generated by Anthropic AI’s Claude. I did this because I’ve gotten very busy with college and my research projects, and I’d rather put out AI-generated content than no content at all. For the record, my friend is not named “Julia”; Claude hallucinated that part. I also added in some markdown formatting to make the presentation a little nicer. For those interested in prompt engineering (or those who just want to read human content), the prompt I used is at the end of the article, and has all the same information.
builds

Subscribe to CrossCurrents

Get notified when new posts are published

My Best Work

Street-Legal Physical Adversarial Rim for License Plates

AI Safety, Interpretability, and Insights from Biology

Can Less Democracy Save Democracy?

Latest

Subscribe to CrossCurrents

Subscribe via Email

Check your inbox

What would you like to see?