No, outages is when you start experimenting with local models and catch up what's new since last outage. If you're a power user, you end up getting to play with local models every week!
I amusingly was doing a "cleanup" of my various harnesses when this happened. Claude Code has a /doctor command which was actually quite helpful, so I decided to swap over to Codex and ask it to do a self-analysis and give me some recommendations if there's something I need to clean up. The response was a connection issue. And so was the next. And the next.
Took me the past 20 minutes to finally check for a status page and realize I hadn't broken something. Not before I created a new project, checked the settings to see my usage numbers, closed and opened the desktop app a couple times, logged out and logged in, used my phone to see if it was a general ChatGPT outage, and generally messing around trying to figure out what I had done.
I mean, you never know... it could have been my prompt that took the whole service down. (Sorry if it was).
At last someone ffin noticed! I've observed it for at least an hour before the announcement.
So much for status reporting from openai. Must have been vibe coded.
was thinking there was something going on with my local network and realized I should look at HN...thank god it's not just me.
This outage started a lot longer than 13mins ago. At least now I have an excuse to leave the office and have a long coffee break.
What... am I supposed to code by hand!?
No, outages is when you start experimenting with local models and catch up what's new since last outage. If you're a power user, you end up getting to play with local models every week!
Don't deploy to production after noon on Friday!
I amusingly was doing a "cleanup" of my various harnesses when this happened. Claude Code has a /doctor command which was actually quite helpful, so I decided to swap over to Codex and ask it to do a self-analysis and give me some recommendations if there's something I need to clean up. The response was a connection issue. And so was the next. And the next.
Took me the past 20 minutes to finally check for a status page and realize I hadn't broken something. Not before I created a new project, checked the settings to see my usage numbers, closed and opened the desktop app a couple times, logged out and logged in, used my phone to see if it was a general ChatGPT outage, and generally messing around trying to figure out what I had done.
I mean, you never know... it could have been my prompt that took the whole service down. (Sorry if it was).