Codecs and the Evolution of Language Models

The project was trying to see what kind of capabilities these large language model have that it goes outside the task that it's been trained to solve. When we were putting in context that came from outside actually the context that the code with the language model would see would not even be code that actually compiles necessarily because we're kind of putting in code that comes from elsewhere. The way we addressed that is that we would define a number of different templates for where we could take code and then train another neural net that would essentially predict the success of each of these different templateYeah I think at the time when we started this project I don't think co-pilot was doing that or it wasn't