This is the kind keeping Atrophic and OpenAI alive.
My Codex agent has been building non-stop for 9 hours straight 🔥
Gave it a massive scope:
build a Mac app for all my content. Calling it Content OS.
Running it in full-auto mode with bypass approvals. Full access to my browser, filesystem, and shell. Going full YOLO.
Set up a 30-min heartbeat automation on the thread in case it drops out of the loop or breaks sandbox to ask for approvals (reminding itself it's supposed to run fully autonomously, no human-in-the-loop).
Also plugged in VAPI via MCP with an instruction:
if for whatever reason you're stuck and can't move ahead because you need action from me, call me on my phone and tell me exactly what the problem is so I can come attend to it.
Hasn't made a single call yet. Didn't get stuck even once so far.
Kicked it off last night.
What I woke up to was nothing short of mind-blowing.
Right now I'm at the gym, haven't even seen the updated output yet (it's a MASSIVE Mac app). Will drop more updates soon.
But first impressions. I'm fucking mind-blown.
- Figured out auth for YouTube Analytics on its own
- Figured out auth for Meta (Instagram Analytics) on its own.
Spent 2 hours driving my browser to solve it
- Integrated an AI layer via OpenRouter so I can talk to my data
- Built a comment response engine with suggested replies using Apple Intelligence (local models)
Will share the full app once it's done.
But boss, it's a definite bye-bye to Claude Code from my end.
Also, hasn't hit rate limits yet. Thanks to Sam resetting the limits post Codex Gen 2 launch yesterday.
BTW, I've never written a single line of code in my life. So don't grill me on security.
Building this as personal software to manage data across the 5M followers I have on IG, YT, X, LinkedIn, and my newsletter.
Will share the full product once it's built. But damn, excited.
Probably will make it free for people to use it once the whole thing is fleshed out!