'Like a billionaire on acid': Star Wars director Gareth Edwards comes out in favour of AI Speaking at Amazon's AI on the Lot event, the Rogue One film-maker Gareth Edwards said'it'll do anything you ask' and'it's going to be better than CGI' Jurassic World Rebirth and Rogue One director Gareth Edwards has enthusiastically endorsed the use of generative AI in film-making, saying "it is a fucking genius at helping you" and "it's going to be better than CGI". Edwards was speaking at AI on the Lot, an event in Culver City, California, organised by Amazon, and in remarks reported by the Hollywood Reporter said: "I can't see a reason why you wouldn't become interested in this stuff as a film-maker. It's so clearly a tool that might be up there with the camera. It's going to be better than CGI." Edwards said that AI is most useful in the preparatory stages of film-making, saying: "It's only good for iteration and discovering what the movie should be, and then once you know what it is, go in and start making it your movie." He added: "It has no taste whatsoever. It is a fucking genius at helping you. I view it like having a second-unit director who is a billionaire on acid. Like, it'll do anything you ask, not a problem. And you'll give it notes, and it'll be like, 'I don't do notes. I'll just do something totally different.' Edwards' positive view of AI was echoed by veteran writer and director Paul Schrader, who was also speaking at the event. In remarks reported by Deadline, Schrader said: "I don't think the real future of AI commercially is in all this flash, all these monsters - that's just jacked-up special effects on steroids," he said. "The real tip of the spear is when we can create an AI protagonist, not a hybrid, and that movie makes money.

Things to Do in L.A. Tap to enable a layout that focuses on the article. Stage 9, also known as the Seinfeld Stage, where the show was produced along Republic Avenue at Radford Studio Center in 2023 in Studio City. Owner Hackman Capital Partners is ceding the 55-acre property to Goldman Sachs. This is read by an automated voice. Please report any issues or inconsistencies here .

Military roads helped the felines domesticate about 2,000 years ago. Breakthroughs, discoveries, and DIY tips sent every weekday. Our pet dogs have been by our side for at least 20,000 years, evolving right along with us. True to their more elusive nature, the timeline of when cats domesticated is more murky. Our homespun feline friends appear to be a more recent arrival in some parts of the world, likely only arriving in Europe about 2,000 years ago.

Things to Do in L.A. Tap to enable a layout that focuses on the article. Santa Monica orders Waymo to stop noisy overnight operations at charging stations. Self-driving vehicles charge at the Waymo station at the corner of Euclid Street and Broadway in Santa Monica. This is read by an automated voice. Please report any issues or inconsistencies here .

Environment Animals Wildlife Bats This tiny bat is one of the world's deadliest hunters Lions wish they killed this well. Breakthroughs, discoveries, and DIY tips sent every weekday. The lion is an undisputed contender for the planet's most iconic predator, but a new study indicates there is an underdog contender coming for its top spot. They're also often more successful at getting the job done. The proof is laid out in a study appropriately published on October 31 in the journal .

What the science says about milk, sleep, and if your cat really loves you. Breakthroughs, discoveries, and DIY tips sent every weekday. Cats are man's best friend--never mind that other animal species. Jokes aside, humans and cats have lived together for thousands of years but not nearly as long as humans and dogs . It makes sense, then, that we don't always understand cats very well.

Things to Do in L.A. Tap to enable a layout that focuses on the article. A'very mean squirrel' is going nuts in this California town. Experts say it's rare for squirrels to attack people, and the most likely reason has to do with humans hand feeding or hand raising the animals. This is read by an automated voice. Please report any issues or inconsistencies here .

's most controversial moment was years in the making. It took many more for the fallout to come into full view. One morning in 2010, Alex Trebek walked onto the IBM campus not far outside New York City and prepared to inspect what would become the most unusual player in's history. The trip, clear across the country from the show's Culver City set, had been carefully planned. David Ferrucci, a computer scientist at IBM, had spent years leading a team to develop what would become the first and, so far, last nonhuman ever to compete on Longtime host Trebek would watch three practice games played with "Watson," as the system was named, and two human contestants. Then the team would be taken to lunch nearby, and Trebek would ultimately take the stage and host two more Watson practice games himself. By then the preparations for a future televised contest with IBM's creation were well underway, but this was the first time Trebek would encounter the technology in person, and his approval was crucial. Ferrucci was eager to show off one element in particular: the display, which had been rigged to show Watson's top three guesses whenever it answered, along with the numerical confidence rate it had in each one. For Ferrucci, this feature was central to demonstrating the computer's language-processing capabilities, because it showed that Watson wasn't just spitting out answers--it was reasoning. If Watson were ever going to be deployed to industries like health care, its human users wouldn't just want to know its best guess. It would be infinitely more valuable to know if Watson was 95 percent confident or just 30 percent, and whether those confidence levels were in line with its actual accuracy rate. It also made for better viewing. Ferrucci had brought his young daughter to the lab earlier in the process and showed her Watson as it played against human opponents. When Watson declined to ring in, Ferrucci's daughter turned to him and asked if the computer had crashed. He struggled to explain that it hadn't--it just wasn't confident enough to hazard a guess.

Citing successes other police departments across the country have seen using drones, the Los Angeles Police Commission said it would allow the LAPD to deploy unmanned aircraft on routine emergency calls. The civilian oversight body approved an updated policy Tuesday allowing drones to be used in more situations, including "calls for service." The new guidelines listed other scenarios for future drone use -- "high-risk incident, investigative purpose, large-scale event, natural disaster" -- and transferred their command from the Air Support Division to the Office of Special Operations. Previously, the department's nine drones were restricted to a narrow set of dangerous situations, most involving barricaded suspects or explosives. Bryan Lium told commissioners the technology offers responding officers and their supervisors crucial, real-time information about what type of threats they might encounter while responding to an emergency.

The diffusion model has demonstrated superior performance in synthesizing diverse and high-quality images for text-guided image translation. However, there remains room for improvement in both the formulation of text prompts and the preservation of reference image content. First, variations in target text prompts can significantly influence the quality of the generated images, and it is often challenging for users to craft an optimal prompt that fully captures the content of the input image. Second, while existing models can introduce desired modifications to specific regions of the reference image, they frequently induce unintended alterations in areas that should remain unchanged. To address these challenges, we propose pix2pix-zeroCon, a zero-shot diffusion-based method that eliminates the need for additional training by leveraging patch-wise contrastive loss. Specifically, we automatically determine the editing direction in the text embedding space based on the reference image and target prompts. Furthermore, to ensure precise content and structural preservation in the edited image, we introduce cross-attention guiding loss and patch-wise contrastive loss between the generated and original image embeddings within a pre-trained diffusion model. Notably, our approach requires no additional training and operates directly on a pre-trained text-to-image diffusion model. Extensive experiments demonstrate that our method surpasses existing models in image-to-image translation, achieving enhanced fidelity and controllability.