Something I appreciate about Open AI & their usage limits: they dont kill a running autonomous codex session mid way.
Anthropic kills everything mid session. Even a running workflow w/ millions of fable tokens in progress gets burned, need to start it over later. It's terrible.
Engineer turned Entrepreneur, turned Engineer, and the cycle continues.
- Fable is the only model I havent had to cuss out even once so far. That's how I know it's competent.
- Man what a crazy time. Spinning up 6 agents to do some work for me before I go to the supermarket.
- Made a little device that manages my claude code’s & codex’s on my server… Simple esp32 s3 chip by waveshare. The orchestrator agent works with voice, controls my device remotely with tools, and controls the server. It’s a cool time to make stuff.
- I’ve got this saying I tell ppl I manage “nobody ever really got fired for adding value.” But I guess I was wrong. Should he have gone through security, legal, compliance etc? Ofc, he works for a massive multi-trillion dollar firm. Should they’ve fired him? Absolutely not.Two months ago I was fired by Google for creating the Google Workspace CLI. It went viral, hit #1 on Hacker News, gained thousands of GitHub stars and many thousands of actual users in just a couple days. It was an incredible, confusing journey, from directors and leaders asking


