A more powerful version of Copilot that can suggest mid-line completions and entire diffs. Trained to autocomplete on sequences of edits, it's quick to understand the change you're making.
I fell in love with Github copilot when it was launched in 2021. It is genius idea: code is low-entropy which means that as programmers we are bottlenecked by keystroke throughput when transferring our ideas into code. (It is still an amazing product.)
But to the entire Cursor team, a few things felt missing. We found ourselves needing to delete characters to nudge Copilot to rewrite them for us — even on simple edits. This needed extra keystrokes, the exact thing we were trying to save. Even worse, the model didn't feel smart. Sometimes it just wouldn't get what we were trying to do, even for edits that to us felt trivial.
Copilot++ is our attempt at solving the right problem. We trained a model can see the edits you have made in the last few minutes. This makes it feel much smarter. We also gave Copilot++ the ability to edit your code, so that a single Tab could finally get you to exactly where you wanted to be.
Copilot++ is still an early version — we plan latency to be cut in half over the next few months, and reduce the false-positive rate. But we already find it really useful, and think you might too. It truly shines when you're in the weeds, coding, and may shine a little bit less bright if you're just trying it out on toy examples.
Please try it out and we would love your feedback.
About Cursor on Product Hunt
“Autocomplete redesigned to predict your next edit”
Cursor launched on Product Hunt on February 29th, 2024 and earned 184 upvotes and 8 comments, placing #22 on the daily leaderboard. A more powerful version of Copilot that can suggest mid-line completions and entire diffs. Trained to autocomplete on sequences of edits, it's quick to understand the change you're making.
On the analytics side, Cursor competes within Software Engineering and Artificial Intelligence — topics that collectively have 509k followers on Product Hunt. The dashboard above tracks how Cursor performed against the three products that launched closest to it on the same day.
Who hunted Cursor?
Cursor was hunted by Sualeh Asif. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Sualeh Asif