"Cursor is hoping Composer will perform in terms of accuracy and best practices as well. It wasn't trained on static datasets but rather interactive development challenges involving a range of agentic tasks. Intriguing claims and strong training methodology aside, it remains to be seen whether Composer will be able to compete with the best frontier models from the big players."
"To address that, Cursor introduced Composer alongside its new multi-agent interface, which allows you to "run many agents in parallel without them interfering with one another, powered by git worktrees or remote machines"-that means using multiple models at once for the same task and comparing their results, then picking the best one. The interface is an invitation to try Composer and let the work speak for itself."
Cursor released Composer, a model trained on interactive development challenges rather than static datasets, targeting accuracy and best practices. Composer arrives with a multi-agent interface that enables running many agents in parallel without interference, powered by git worktrees or remote machines, allowing multiple models to tackle the same task and comparing their outputs. Developer reaction is mixed so far, with some perceiving Composer as promising but too expensive relative to capability gaps versus major frontier models like Anthropic's Claude. Cursor 2.0 includes additional features and fixes available in the changelog.
Read at Ars Technica
Unable to calculate read time
Collection
[
|
...
]