Pinned
We’re introducing Cursor 3. It is simpler, more powerful, and built for a world where all code is written by agents, while keeping the depth of a development environment.
00:00
Cursor
461 posts
Cursor
@cursor_ai
Coding agent for building ambitious software
Joined August 2023
- Cursor reposted
We're trying a new experiment at @cursor_ai - interviewing devs we admire. I chatted with @oneill_c & @part_harry_ from @baseten about how they use coding agents. We discussed their current dev workflows & some predictions for the future. Check it out below!
00:00 - Auto-review is now the default for all new users. A classifier subagent reviews actions in context before deciding whether to allow, block, or ask for approval. Our evals show it's 97% accurate, with most misses near ambiguous edges.
- Cursor’s code review agent is now over 3x faster, 22% cheaper, and finds 10% more bugs. You can also use /review to run Bugbot locally to catch and fix issues before pushing code.
00:00 - Replying to @cursor_aiSee how Claude Fable 5 compares across every model: cursor.com/evals
- Claude Fable 5 is now available in Cursor. It sets a new state of the art on CursorBench at 72.9%, 8 points above the previous best.
- Replying to @cursor_aiGive Cursor visual prompts to shrink the gap between what you see and what the agent understands. Learn more:
- With Design Mode, you can now point, draw, or talk to update your UI.
00:00 - Replying to @cursor_aiCursor can now show your agent's context usage as an interactive report in a canvas. The context explorer breaks down where tokens go across the system prompt, tool definitions, rules, skills, and more.
00:00
