Hey d,

I didn't sleep much last night. I was up pushing Sol to fix things that GPT-5.5 couldn't.

I got early access to GPT-5.6 yesterday, and I had agents working on both macOS and iOS apps (and QA tooling). These models are super capable, but they have different strengths and weaknesses.

I had them work on SwiftUI for an iPhone app today.

Watch: GPT-5.6 vs Fable 5: 4 UIs, Judged Blind, 1 Winner​

​

Can you tell which model made each UI? Hint: one is not like the others.

Sponsored by Superhuman The Gold Standard for AI News AI will eliminate 300 million jobs in the next 5 years. Yours doesn't have to be one of them. Here's how to future-proof your career: • Join the Superhuman AI newsletter – read by 1M+ professionals • Learn AI skills in 3 mins a day • Become the AI expert on your team Start learning AI now

Now, we have access to really powerful models. It's going to change the direction of work. It's exciting and a little ... crazy.

Talk soon,
Paul Solt

P.S. Working on an iOS/macOS app? I do 1:1 App Strategy Sessions.
​Book a time and let's talk about your app.​

I had a great session today about app direction. If you've ever wanted to publish an app, but you're stuck. This session might be the direction you need.