Cursor

Radar Signals

24 linked signals.

• No model dominates every kind of task. Grok 4.5 offers strong value on routine tasks. GPT-5.6 Sol is effective on planning and codebase comprehension. Opus 5 excels for execution-heavy work, and Fable 5 on debugging andCursor · 4d
• Cursor now supports Agent Plugins, an open standard for bundling skills and MCP servers for use across agents. https://x.com/vercel/status/[private phone]?s=20Cursor · 4d
• Here's how we built it: https://cursor.com/blog/how-cursor-router-works?v=2Cursor · 4d
• Cursor Router keeps improving from millions of in-product user interactions each week. We intelligently classify and route requests, lowering latency and reducing cost based on the task.Cursor · 4d
• Cursor Start also includes: - Autonomous cloud agents that ship work while you're away - Cursor for iOS to steer them from your phone - Plugins, MCP servers, hooks, and skills to extend your workflow Learn more: http://cCursor · 14d
• Today we're launching Cursor Start, a new ₹649/month plan for developers in India. Start includes generous access to Grok 4.5 and Composer, so you can plan, build, test, and ship with agents every day.Cursor · 14d
• Kimi K3 is now in Cursor! It scores close to the frontier on CursorBench. It's available on US-based inference thanks to our partners Fireworks, Together, and Baseten. Zero Data Retention is also supported.Cursor · 14d
• See how all of the models compare here: http://cursor.com/evalsCursor · 17d
• Our hope is that this lowers the barrier to AI research, so more labs can train models efficiently. Here's how we built it: http://cursor.com/blog/mixture-of-kittensCursor · 6d
• Claude Opus 5 is now available in Cursor! It matches Fable 5 on CursorBench (66.7 vs 66.5 at default effort) at half the price. Unlike Fable, it's also compatible with Zero Data Retention.Cursor · 17d