Last week, Dan Blanchard, the maintainer of chardet—a Python library for detecting text encodings used by roughly 130 million projects a month— released a new…
I find “from scratch” a questionable claim as well. The model was probably trained on the code it is supposed to replace. Interfacing with the concrete tests and interfaces makes the result even more likely to be and puts it conceptually closer to the original code fed as training data.
I find “from scratch” a questionable claim as well. The model was probably trained on the code it is supposed to replace. Interfacing with the concrete tests and interfaces makes the result even more likely to be and puts it conceptually closer to the original code fed as training data.