About us
Change Log
Here are all of the features introduced in each release. If you have a Double account, you’ll also receive a monthly digest to keep up to date. Follow us on X to stay up to date with updates.
Note that not all of the changes here are reflected as extension versions, some changes are only on our backend, website, and other non-extension related services.
July 24th, 2024
- Added Mistral Large 2, and DeepSeek Coder V2 (7/24) to our selelection of supported models.
July 23rd, 2024
- Added Llama 3.1 405B, the first frontier-level open source AI model with 128k context length, to our selelection of supported models. Also added Llama 3.1 70B and LLama 3.1 8B.
July 16th, 2024
- Fixed a bug in Jupyter notebooks where copy-paste from Chat would not work.
- Fixed various other bugs that would occasionally cause issues connecting to our servers.
July 15th, 2024
- We have released a new custom Autocomplete AI model and are rolling it out to all users over the next week.
July 12th, 2024
- Disabled sticky autoscroll for Chat based on user feedback.
July 10th, 2024
- We now stream the code suggestions made by Inline Edits (preview) so that results are shown a lot faster.
- Changed the default model for Inline Edits (preview) to Claude 3.5 Sonnet for faster and higher quality code generation.
July 8th, 2024
- Increased the maximum per message token count for Chat from 4,000 to 20,000 tokens.
June 26th, 2024
- Overall platform reliability improvements, and streamlining and bug fixing to continue improving the new Inline Edits (preview) feature.
June 20th, 2024
- Added Anthropic’s new Claude 3.5 Sonnet to our selection of supported models
June 18th, 2024
- Changed the default model for the new Inline Edits (preview) feature to DeepSeek Coder V2.
June 17th, 2024
- Added the new DeepSeek Coder V2 to our selelection of supported models.
June 14th, 2024
- Reliability improvements for Inline Edits (beta). Fixed unnecessary empty lines always preceding the edit, and subsequent lines disappearing after accepting an edit.
June 7th, 2024
- Improved Autocomplete caching. Cache hit rate should now be higher and respond faster. Overall Autocomplete should feel faster.
May 27th, 2024
- Launched Inline Edits for beta testing. This feature allows you to highlight any code, press
Option+O
, write your instructions, and see the output in diff style.
May 13th, 2024
- Added OpenAI’s new GPT-4o to our selelection of supported models
April 22nd, 2024
-Removed the need for SMS verification for new users creating an account.
April 18th, 2024
- Added Meta’s new LlaMA-3 70B to our selelection of supported models
April 13th, 2024
- UI improvements on how code snippets are shown in the Chat history
April 9th, 2024
- Added the new and improved GPT-4 Turbo (2024-04-09) model from OpenAI, benchmarks indicate that this is OpenAI’s most capable coding model.
- Started this change log! 👋
Was this page helpful?