TabNine: Autocompletion with deep learning
7 months ago by b | 13 facts | 0 comments | 36 votes

  • We’re adding a deep learning model which significantly improves suggestion quality. -
  • The model also uses documentation written in natural language to infer function names, parameters, and return types: -
  • In the past, many users said they wished TabNine came with pre-existing knowledge, instead of looking only at the user’s current project. -
  • Deep TabNine requires a lot of computing power: running the model on a laptop would not deliver the low latency that TabNine’s users have come to expect. -
  • So we are offering a service that will allow you to use TabNine’s servers for GPU-accelerated autocompletion. -
  • See all the facts

No comments yet.
Be the first to leave one. login or register.

Story Info
  • Upvotes: 36
  • Downvotes: 0
  • Poster: b