A world model inside a world model 🌏 https://t.co/XQCFzy2pjc
— hardmaru (@hardmaru) 7 août 2025
A world model inside a world model
By
–
A world model inside a world model 🌏 https://t.co/XQCFzy2pjc
— hardmaru (@hardmaru) 7 août 2025
A world model inside a world model
By
–
Connecting MCPs to GPTs with custom actions is much harder than it needs to be, we wrote up a guide here for it:
By
–
It’s now easier to steer the agent while it’s running. Sending a new message will schedule at the ideal time, usually after a tool call, versus queuing and waiting until the agent finishes. pic.twitter.com/NOfjlYlSSC
— Cursor (@cursor_ai) 6 août 2025
It’s now easier to steer the agent while it’s running. Sending a new message will schedule at the ideal time, usually after a tool call, versus queuing and waiting until the agent finishes.

By
–
Background Agents can be used directly inside GitHub pull requests. Tag @cursor and the agent will read the context, apply the fix, and push a commit. We’ve also reduced the startup time by over 70%!
By
–
Cursor 1.4 is out with a significantly more capable agent. It’s now much better at challenging and long-running tasks, especially in large codebases. We’ve also given the agent better tools, made token usage more efficient, and improved code editing accuracy.
By
–
My AI auto-releases new versions of itself as needed for marketing purposes.
By
–
Interesting, it looks like @cursor_ai offer a feature like this too now (I thought they were editor only, didn't know they had a browser story) Maybe if they marketed this as an "asynchronous coding agent" people like me would have an easier time understanding what it does!
By
–
Huh! Yeah that's absolutely the asynchronous coding agent pattern, thanks for the tip
By
–
LangChain's new Open SWE tool, released this morning (and MIT licensed) calls itself an "asynchronous coding agent" too
By
–
Jules used that term in the headline of their general availability announcement today: "Jules, our asynchronous coding agent, is now available for everyone."