







Watching OpenAI’s new o3 model guess where a photo was taken is one of those moments where decades of science fiction suddenly come to life. It’s a cross between the …
AI’s Jurassic Park Moment
Something incredible is happening in AI right now, and it's not entirely to the good. Everybody is talking about systems like chatGPT (OpenAI), Dall-E 2, and Lensa that generate text and images that look remarkably human-like, with astonishingly little effort.

Oculus Executive Calls For 3D Equivalent Of JPEG To Build The Metaverse
A new standard for 3D scenes is gaining momentum with support from graphics industry leaders, potentially laying the groundwork for science fiction’s “metaverse” to be realized.

A Camera, Not an Engine II
Further thoughts on photography in latent space, now with agents!

The Ghost Stays in the Picture, Part 1: Archives, Datasets, and Infrastructures - Flickr Foundation
Eryk Salvaggio is a 2024 Flickr Foundation Research Fellow, diving into the relationships between images, their archives, and datasets through a creative research lens. This three-part series focuses on the ways archives such as Flickr can shape the outputs of generative AI in ways akin to a haunting.

Inside Looks: A Mark III Preview
Today launched a public preview of Halide Mark III, the next generation of our flagship photography app. It's still a work in progress, but we're ready to start sharing what we've worked on for the past year through a series of app updates alongside posts like this. Today, we're diving into Looks.

Twilight of the Spielberg Image
Steven Spielberg's career wrestles with the power and meaning of image-making, and his sci-fi "Disclosure Day" makes this its very subject.

moonshotai/Kimi-K3 at 2496450e92e425c886db095102a52a6682ca3970
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Eyes on the Solar System - NASA/JPL
Explore the 3D world of the Solar System. Learn about past and future missions.

Anthropic has caught up to OpenAI in image understanding
But neither one is all that good.

OpenAI goal is to build a world simulator - that learns the dynamics of the 3D real world - from videos & language descriptions. They claim the work indicates that training on ever larger datasets is a promising direction for learning such world models. But they are wrong:
OpenAI goal is to build a world simulator - that learns the dynamics of the 3D real world - from videos & language descriptions.They claim the work indicates that training on ever larger datasets is a promising direction for learning such world models.But they are wrong:— Chomba Bupe (@ChombaBupe) February 16, 2024
Explore Public Domain Images & Videos | Arkivism
Search 4 million+ public domain and copyright-free images and videos by describing what you're picturing.

Imagining the Voyager 1 probe's journey through space when humanity no longer exists
More photos at www.flickr.com/elentir

OpenAI changed AI Video FOREVER | Sasha Grey
Arkivism: search millions of public-domain images
Search over 3 million public-domain artworks, photographs and illustrations by describing what you're picturing. Free, forever.

Gazing through a lens, I invent as much as I reveal | Psyche Turning Points
For years I watched people through cameras and screens, filling in the blanks and calling it truth

Image generation | OpenAI API
Learn how to generate or edit images with the OpenAI API and image generation models.
