Toggle light / dark theme

The California PUC granted Waymo a permit to operate 24 hours/day in San Francisco taking select members of the public for rides with no safety driver in the vehicle. Waymo says it will begin this shortly. This comes on the heels of them expanding such service in Phoenix, as reported in my article on how the death of self-driving cars has been greatly exaggerated earlier this week.

This service will be with “trusted testers” rather than members of the broad public that can ride in Chandler and Phoenix, Arizona.


Waymo gets a permit to take the public and will start running with trusted testers. They also start in LA and show off their new robotaxi. Cruise also ups its game. Zoox got into an accident but it was in manual. Aurora reminds us they do more than trucks.

It has been built to be a self-sustaining floating city.

Designer Pierpaolo Lazzarini has proposed a concept for a bold and innovative terayacht which is a giant floating continent double the size of the Roman Colosseum, as first reported by DesignBoom last Friday. It’s called the Pangeos watercraft and it consists of a floating city that includes various hotels, shopping centers, parks, as well as ship and aircraft ports.

Inspired by Pangea.

The concept can host up to 60,000 guests in the middle of the sea surrounded by water and is in the shape of a gigantic turtle.


Lazzarini Design Studio.

Diehard Elon Musk fans have created a 30-foot-long monument dedicated to their hero – and it cost them over half a million pounds ($600,000).

The unique piece sees the richest man in the world’s head attached to a goat’s body while riding a rocket.

It’s the brainchild of cryptocurrency firm Elon GOAT Token ($EGT), who later this month plan to present it to the billionaire at his Tesla workplace in Austin, Texas.

Flying car startup Airspeeder has completed what it’s referring to as the “world’s first electric flying car race” in the South Australian desert.

While the two competing pilots were steering the two full-scale flying cars remotely, it still made for an epic launch of a brand new kind of motorsport, as seen in a promotional video of the event.

“This is just the start, this first race offers only a glimpse of our promise to deliver the most progressive, transformative and exciting motorsport in the world,” Airspeeder founder Matt Pearson said in a press release.

Recent progress in generative models has paved the way to a manifold of tasks that some years ago were only imaginable. With the help of large-scale image-text datasets, generative models can learn powerful representations exploited in fields such as text-to-image or image-to-text translation.

The recent release of Stable Diffusion and the DALL-E API led to great excitement around text-to-image generative models capable of generating complex and stunning novel images from an input descriptive text, similar to performing a search on the internet.

With the rising interest in the reverse task, i.e., image-to-text translation, several studies tried to generate captions from input images. These methods often presume a one-to-one correspondence between pictures and their captions. However, multiple images can be connected to and paired with a long text narrative, such as photos in a news article. Therefore, the need for illustrative correspondences (e.g., “travel” or “vacation”) rather than literal one-to-one captions (e.g., “airplane flying”).