These past have been super busy for me - mostly with getting all the developer materials for Gemini SDK for Swift in place. Gemini is Google's largest and most capable AI model yet.

One of its key capabilities is reasoning about multi-modal input: for example, you can pass in the confused Travolta meme and ask it what happens in the scene, who's the actor, and why their character is confused in this scene.

After the launch, I've been playing around with the SDK a lot more, and started building an LLM-powered text adventure for one of my favourite books. Can't wait to share more with you!

I hope y'all get a chance to wind down and celebrate some of the achievements you accomplished this year. I, for one, look forward to spending some time with my family, enjoying good food, playing some games, and digging into that giant pile of books that has accumulated over the past couple of months...!

Thanks for being a subscriber!

Peter Friese  



AI and ML




Computer History