11–20 of 31 posts
There is no ability to share the current buffer(s) for context, no tool support. This seems like a checkbox release. You’re better off using CodeCompanion with Amazon Bedrock, which includes the added benefit of sovereignty.
This doesn’t even come close to CodeCompanion[1], which doesn’t require any new LSP config/dependencies or filetype limitations. There is no ability to share the current buffer(s) for context, no tool support. This seems like a checkbox release. You’re better off using CodeCompanion with Amazon Bedrock, which includes the added benefit of sovereignty. [1]: https://github.com/olimorris/codecompanion.nvim
This doesn’t even come close to CodeCompanion[1], which doesn’t require any new LSP config/dependencies or filetype limitations. There is no ability to share the current buffer(s) for context, no tool support. This seems like a checkbox release. You’re better off using CodeCompanion with Amazon Bedrock, which includes the added benefit of sovereignty. [1]: https://github.com/olimorris/codecompanion.nvim
CodeCompanion doesn’t have tab completion right? I love Neovim but Cursor’s tab completion is just next level and I haven’t found any nvim plugin that comes close to it.
It’s like Amazon’s Chime to everyone else’s Zoom. It works, but unless you have no other option it’s not clear why I’d choose to use it.
Can't wait for my code being used as training data for Amazon to make a profit
Earlier quoted context omitted.
Isn’t that only the case for the free tier, which is only fair?
Yes but restating the obvious sometimes helps to underscore who provides free work for whom. In this day and age it is often the 'user' who does the free labor. Especially, when there was normalized narrative (even before LLMs - with the crowd source) that user is the one being served.
So while restating the obvious in these cases is very good, it's also good to point out when.
Can't wait for my code being used as training data for Amazon to make a profit
Isn’t that only the case for the free tier, which is only fair?
Most big players in the LLM field are getting their training data by at-least shady, if not illegal measures.
And if they don't care about laws on one side, why should anyone believe that they care on the other?
Amazon already uses their customers privat data to train models [1].
[1] https://www.ftc.gov/business-guidance/blog/2023/06/hey-alexa...
Earlier quoted context omitted.
CodeCompanion doesn’t have tab completion right? I love Neovim but Cursor’s tab completion is just next level and I haven’t found any nvim plugin that comes close to it.
GitHub Copilot nvim plugin[1] has autocomplete with ghost text, but of course it requires you use GitHub Copilot :) [1]: https://github.com/github/copilot.vim