LLMs understand nullability

Inside the CodeBot: A Gentle Introduction to How LLMs Understand Nullability Alex Sanchez-Stern and Anish Tondwalkar The last five years have shown us that large language models, like ChatGPT, Claude, and DeepSeek, can write code in many domains, to huge excitement: many claim to be using these models to write entire web servers and apps from scratch. These tools have opened up programming to a whole new class of people who consider themselves non-technical. A gif of github copilot completing a phone number validating function as the user types But there are still many unanswered questions that someone trying to understand or even use these tools might have. For example, how often, and in what situations, can LLMs write correct code entirely on their own? And, maybe more importantly, but harder to answer: Do LLMs “understand” the code they are writing? Understanding is a tricky concept to measure. Some would argue that sentience precedes understanding, and so that LLMs can’t ha ... Read full article.