LLMs continue to push the boundaries of content generation, but they can struggle when the output needs to follow very strict rules, like writing code, generating formulas, or creating markup languages (like JSON or HTML). This begs the question: how do we generate highly structured outputs that...
I’ve been diving back into static analysis and programming language theory after a 4 year hiatus. Getting re-acquainted with papers in the field has been humbling, and can feel like solving a puzzle with infinite pieces. Writing and summarizing helps me make sense of it all, so I wanted to share...
During YC, the group partners’ constant refrain about remaining intellectually honest and prioritizing customers needs seemed almost redundant. Yet I fell into the very trap they had repeatedly warned against—a humbling reminder that even the clearest advice can’t immunize us against our own blind...
I started using Copilot as a GitHub employee when it first emerged, long before it was available publicly. I found myself skeptical. The early versions felt noisy and distracting—auto-complete suggestions caused more interruption than inspiration. The user experience fundamentally scattered my...