My dream last night was that Apple guy running down the stairs playing in a loop.

Can we all stop now please? 馃檹
0
0
0
17
So apparently I'm a Rust fanboi, just for trying to be helpful to a few folks on stackoverflow
0
0
0
13
Programming language text books are outdated the moment they are printed
0
0
0
16
It took @Apple 48 years to add true dark mode. No your T-10 day old app doesn't need dark mode
0
0
0
20
Has anyone built an Alexa skill to talk to ChatGPT API?
0
0
0
14
Today was one of the best WWDC events I've seen in a while
1
0
0
14
Replying to @soiglac
Most excited about Siri getting a makeover finally, so I can use it more than for just setting timers
0
0
0
16
BenjaminCrouton retweeted
Everyone's expecting a reborn Siri at WWDC today. Well, Apple already published a paper on it that disclosed way more details than what we expect from Apple. It's called "Ferret-UI", a multimodal vision-language model that understands icons, widgets, and text on iOS mobile ut their spatial relationships and functional meanings.

Example questions you can ask Ferret-UI:
- Provide a summary of this screenshot;
- For the interactive element [bbox], provide a phrase that best describes its functionality;
- Predict whether the UI element [bbox] is tappable.

With strong screen understanding, it's not hard to add action output to the model and make it a full-fledged on-device assistant.

The paper even talks about details of the dataset and iOS UI benchmark construction. Extraordinary openness from Apple! They are truly redefining their AI research branch.

The paper was silently released with little PR fanfare in April. You still have enough time to warm up before WWDC: arxiv.org/abs/2404.05719
45
289
1,550
303,606
BenjaminCrouton retweeted
Hey @google, some free branding for you

Awesome Google Intelligence

Get that AGI inside
28
27
511
110,297