Tried Zed AI for a bit as a heavy user of Cursor, a few thoughts
- I like that they are trying something different with the assistant panel view by providing end users full control of the context as opposed to Cursor's "magic" approach. There is a huge tradeoff between the granularity of control and efficiency however. The friction for manually filling in context for the assistant window might repel devs from using it constantly.
- Zed AI is still missing a lot of UX details in terms of their inline assistant capabilities. e.g. pressing ctrl+? for inline assist only selects the current line, and users will have to manually select a block of code for inline assist, which is really annoying. In cursor, cmd+k automatically selects the surrounding code block
- Definitely a huge plus that we get to choose our own LLM providers with Zed AI.
Really like the idea of a tree-based browsing history. It is more in tune with the graph-traversal nature of browsing the internet, and could be extremely useful for people who conducts extensive reading or research on the internet. Honestly feel like this should be an option for more web browsers as an alternative to the 1D, flat structure of tabs.
I wonder what the standard approach is when the LLM does not return valid JSON data? Do you skip the input data all together, or use the parsing error to generate a valid JSON?
Looks nice! I have been using empty git commit messages for journaling in the past few months and found that I'm more willing to journal in the command line with this git-abuse than most applications specifically designed for journaling. Don't know if anyone else has tried this