Switching Composer 2.5 from Fast to non-fast every time something is executed could be one of the most annoying things about @cursor_ai
Subagents auto to Fast, Every time I hit build same thing. It does not inhert speed preference.
Anyone else seeing a 2% drain on weekly status per day without usage of Codex? @thsottiaux@OpenAI
I way over did it so I stopped using it for 5 days and its still been going down roughly 2% a day without any usage.
I’d like to thank @opencode@FactoryAI@cursor_ai@conductor_build@OpenAI for building amazing tools and being so developer friendly. You are all truly making AI an accessible and developer friendly space to learn, build, and deploy in. Keep up the great work!
Just leveraged @opencode with codex 5.3 to turn 360 Videos into an interactive iPad app, and then with the same setup - a VR experience with Unity and Quest 3.
I wont say if it was the Desktop or CLI
Agent Skills are now available in Google Antigravity!
Skills are an open standard to extend what your agent can do. Whether it's project-specific workflows or global utilities, you can now package knowledge into reusable skills.
I’m hoping that @OpenAI’s garlic model is efficient enough to reduce reliance on subsidized plans or at least make thing like @cursor_ai ultra possible for working on several projects at a time.
Scoop: xAI staff had been using Anthropic’s models internally through Cursor—until Anthropic cut off the startup’s access this week.
Here’s what xAI cofounder Tony Wu sent to staff on Wednesday according to a copy of the internal Slack message I viewed:
“Hi team, I believe many of you have already discovered that anthropic models are not responding on cursor. According to cursor this is a new policy anthropic is enforcing for all its major competitors.
This is a both bad and good news. We will get a hit on productivity, but it rly pushes us to develop our own coding product / models. We're at a time in which Al is now a critical technology for our own productivity. This coming year is rly going to be wildly exciting for all of us.
The team is rapidly developing our own models / product. We will have something to share with everyone soon. In the meantime, you may still try all different kinds of models in grok build.”
Anthropic declined to comment. A Cursor spokesperson directed me to Anthropic for comment. xAI did not respond to request for comment.
Tried @cursor_ai ultra and ended up chewing through 10% of ultra sub in 1 day (Opus 4.5 Planning, Gemini 3 Flash Coding). This is working with 1-2 projects and only for a 4-5 hours of work.
Is this normal?
You are building SaaS's and have $400/mo, and will hit the triple comma for token usage. What does your AI workflow look like, i.e. Warp with @FactoryAI, Cursor Ultra, ect.
For Pre-Seed CRMs, whats everyone's go to?
Do you just build your own or are there CRMs that you feel really changed our lead and relationship management?
I am truly enjoying the @FactoryAI , but I keep getting "> Error: undefined is not an object (evaluating 'A.match')" in VS Code.
Anyone have an idea whats going on with that?
I've had to switch off of it because of the scrolling bug and this (I want to go back lol).
When coding with Agentic AI solutions such as Claude Code or Codex, are you using an IDE or Terminal. I'm also curious if your workflow is building multiple projects at once.