The AI agent I built just booked me a Zoox through an API I didn’t know existed.
"Call me a Zoox and text me updates". I was half joking, but Solid wasn’t.
Solid reverse-engineered the app, retrieved my user token, and called the underlying API directly to book me a car.
Then
A beta user texted me this morning, raving about our calling agent feature.
I thought she was drunk. We haven’t built a calling feature.
So I pulled up the log. She was not drunk.
She had asked Solid to call local suppliers and check if they have a part in stock. That was the
One by one, new models have knocked down every logic puzzle I've ever collected, except one.
GPT-5.6 just solved it - in 57 minutes.
Fable 5 ran out of output tokens trying.
I need a new puzzle.
(Puzzle and transcript in the comments)