Agentic search benchmarks are a big gap up. let's see Codex release later today

First OpenAI Engineering blog? I'm definitely interested in seeing more and how they handled the rapid growth.

There was a lot of downtime...

I think they handled the massive growth by a lot of 2am emergencies and editing config files directly in production in the hope of fixing fires.

The image of the person is hosted under their website as `/images/goat.jpg.webp`, interesting. Goat.

Great piece, thanks for the write up.

The correct link is https://search.google.com/search-console

The domain listed on the GitHub repo redirects too many times.

That should be fixed now. It was a misconfiguration of CloudFlare SSL with GitHub Pages.

GPT-5 coming Thursday.

Is this the stealth models horizon alpha and beta? I was generally impressed with them(although I really only used it in chats rather than any code tasks). In terms of chat I increasingly see very little difference between the current SOTA closed models and their open weight counterparts.

Their tokenization suggests they're new Qwen models AFAIK. They tokenize input to the exact same # of tokens that Qwen models do.

How much hype do we anticipate with the release of GPT-5 or whichever name to be included? And how many new features?

Excited to have to send them a copy of my drivers license to try and use it. That’ll take the hype down a notch.

Imagine if it's called GPT-4.5o

Really cool stuff, keep it up.

thanks!!!

Insane dedication.

They're the same company that ran into this, at least they're learning! > How WebSockets cost us $1M on our AWS bill