Tag: ai
All the articles with the tag "ai".
I tried to catch a language model making a math mistake. My first accepted paper is about why it did not work.
Published: at 03:30 PMMy MATH-AI workshop paper at NeurIPS 2026 tests whether drift in a language model's hidden state can flag and fix math errors mid-solution. It does neither, and getting to that answer taught me more than a positive result would have.
AI security is not web security
Published: at 02:45 AMPrompt injection, the lethal trifecta, and why the input validation habits from web security stop working once a language model is reading your data.
Giving Dear Future Me a voice at the VoiceOS hackathon
Published: at 01:00 AMAt the VoiceOS hackathon we turned Dear Future Me from a website with forms into an iPhone app you just talk to. VoiceOS has changed how I work since.
Sinkhorn distance and optimal transport, explained with piles of sand
Published: at 09:55 PMOptimal transport measures how far apart two distributions are by asking how much work it takes to move one onto the other. Sinkhorn makes it fast.