Category: Code & Math AI
-
Code & Math AI: When Proving Programs Correct Became Practical
The year AI stopped guessing and started proving — how agentic theorem proving, I/O-optimal attention, and domain specialization converged (56 papers surveyed, 33 miscategorized filtered out) — In May 2025, if you asked an LLM to write a program and formally verify it, you’d get back plausible-looking code that probably didn’t compile and definitely hadn’t…