I really wonder why dynamic learning hasn't been explored more. It would be a huge moat for the labs (everyone would have to host and dynamically train their own model with a major lab). Seems like it would make the AI way smarter too.
Local models just aren't there yet in terms of being able to host locally on your laptop without extra hardware.
We're hoping that one of the big labs will distill an ~8B to ~32B parameter model that performs SOTA benchmarks! This would be huge both in cost and probably make it reasonable for most people to code with agents in parallel.
This is a great suggestion. We're actually storing the input/output costs of most models, but aren't computing cost estimates yet. Definitely something to add. My only hesitation is that token-based cost estimates may not be accurate (most models do not provide their tokenizers, so you have to eg. estimate the average number of characters per token in order to compute the cost, and this may vary per model).
It'd probably be useful to just show cost after the fact based on the usage returned from the API. Even if I don't know how much my first request will cost, if I know my last request cost x cents then I can probably have a good idea from there.
You're right that extensions do manage fine - the main differences right now are UX improvements (many of them are mentioned above). I can see the differences compounding at some point which is why we're focused on the full IDE side.
The extensions API lets you control the sidebar, but you basically don't have control over anything in the editor. We wouldn't have been able to build our inline edit feature, or our navigation UI if we were an extension.
Big fan of Continue btw! There's a small difference in how we handle inline edits - if you've used inline edits in Cursor/Windsurf/Void you'll notice that a box appears above the text you are selecting, and you can type inside of it. This isn't possible with VS Code extensions alone (you _have_ to type into the sidebar).
If I understand your question correctly - Cline and Roo both display diffs by using built-in VS Code components, while Cursor/Windsurf/Void have built their own custom UI to display diffs. Very small detail, and just a matter of preference.
It's about whether the tool can edit just a few lines of the file, or whether it needs to stream the whole file every time - in effect, editing the whole file even though the end result may differ by just a few lines.
I think editing just a part of the file is what Roo calls diff editing, and I'm asking if this is what the person above means by line edits.
Thanks for the suggestions - these issues have been a bit painful for us, and we will probably fix them in the next major update to Void.
Believe it or not, the logo similarity was actually unintentional, though I imagine there was subconscious bias at play (we created ours trying to illustrate "a slice of the Void").
This is a good question. Because we're open source, we will always allow you to host models locally for free, or use your own API key. This makes monetization a bit difficult in the short term. As with many devtool companies, the long-term value comes from enterprise sales.
One of the founders here - Void will always remain open source! There are plenty of examples of an open source alternative finding its own niche (eg Supabase, Mattermost) and we don't see this being any different.
