Toward deep-learning models that can reason about code more like humans.

Researchers propose a method for finding and fixing weaknesses in automated programming tools.
A machine capable of programming itself once seemed like science fiction. But an exponential rise in computing power, advances in natural language processing, and a glut of free code on the internet have made it possible to automate at least some aspects of software design. 
“Unless you’re really careful, a hacker can subtly manipulate inputs to these models to make them predict anything,” says Shashank Srikant, a graduate student in MIT’s Department of Electrical Engineering and Computer Science. “We’re trying to study and prevent that.”
Right. Just watch. Nothing is tamper proof....

https://news.mit.edu/2021/toward-deep-learning-models-that-can-reason-about-code-like-humans-0415

This is my first notebook. Inside is the original design for my book. I go back to it often to remember my original intent. Because no matter where I go with the story, I seem to always come back to the beginning.