11. C Claude Haiku 5.5 is priced at $0.10/M input and $0.50/M output tokens, or $0.50/M and $2.50/M above ... Claude Haiku 5.5 is priced at $0.10/M input and $0.50/M output tokens, or $0.50/M and $2.50/M above 100k input tokens. Claude Sonnet 5.5 cache reads are also now $0.10/M tokens, do 10/08 02:14 ♡
12. Claude Haiku 5.5 is now available in Cursor! On shorter requests, it costs 10x less than Claude Hai... Claude Haiku 5.5 is now available in Cursor! On shorter requests, it costs 10x less than Claude Haiku 4.5. Turn it on in Cursor Settings > Models. 💬 179 🔄 126 ❤️ 27 10/08 02:14 ♡
13. D Download the Cursor iOS app and pair it with your computer: https://t.co/iHOGAsDRpV On Enterprise? ... Download the Cursor iOS app and pair it with your computer: cursor.com/mobile On Enterprise? Ask your admin to turn it on. Learn more: cursor.com/changelog/remo… 💬 8 ǵ 10/07 07:47 ♡
14. T The agent runs on your computer, so it keeps working even if your phone loses signal. The agent runs on your computer, so it keeps working even if your phone loses signal. 💬 5 🔄 6 ❤️ 122 👀 23409 📊 16 ⚡ Powered by xgo.ing 10/07 07:47 ♡
15. Y You can now control agents on your computer from your phone. Check in, reply, or start new tasks fr... You can now control agents on your computer from your phone. Check in, reply, or start new tasks from the Cursor iOS app. Your browser does not support the video tag. 🔗 Vie 10/07 07:46 ♡
16. S Steering and system prompts work with local TypeScript agents. Background subagent results come back... Steering and system prompts work with local TypeScript agents. Background subagent results come back locally in TypeScript and Python. See everything new in the SDK: cursor.com/doc 10/06 00:09 ♡
17. You can also replace Cursor's system prompt with your own. Rules, skills, and tool schemas still loa... You can also replace Cursor's system prompt with your own. Rules, skills, and tool schemas still load. We're enabling it account by account. 💬 4 🔄 1 ❤️ 38 & 10/06 00:09 ♡
18. Custom tools can now carry MCP annotations like readOnlyHint and destructiveHint, so the model can t... Custom tools can now carry MCP annotations like readOnlyHint and destructiveHint, so the model can tell a lookup from a delete before it calls one. 💬 6 🔄 0 ❤️ 44 &# 10/06 00:09 ♡
19. Background subagents now report back. Their results return to the parent as a follow-up turn on the... Background subagents now report back. Their results return to the parent as a follow-up turn on the same run, so stream() and wait() carry through until every subagent finishes. &# 10/06 00:09 ♡
20. Y You can now steer Cursor SDK agents while they run. run.steer() adds your message to the next turn.... You can now steer Cursor SDK agents while they run. run.steer() adds your message to the next turn. If a subagent is mid-task, it moves to the background and keeps working. Your br 10/06 00:08 ♡
