Pre-trained language models are effective in a variety of natural langua...
In this 4-page manuscript we discuss the problem of long-term AI Safety ...
The relationship of comments to code, and in particular, the task of
gen...
Given the current transformative potential of research that sits at the
...
Berger et al., published in TOPLAS 2019, is a critique of our 2014 FSE
c...
Natural code is known to be very repetitive (much more so than natural
l...
Code corpora, as observed in large software systems, are now known to be...