OpenAI shut down development of its Sora video generator, derailing the $30M AI-animated feature 'Critterz' just before its Cannes premiere, highlighting the dependency risks of AI filmmaking.
https://preview.redd.it/nz3hvn6z6m3h1.png?width=800&format=png&auto=webp&s=401f2cbae2c6f79741134bc8d01626f35412bf6a So OpenAI basically killed off development for their Sora video generator, and it completely wrecked the animated movie "Critterz" by Chad Nelson, who's actually OpenAI's creative strategist and a producer. The movie missed its big premiere at the Cannes Film Festival because of it. The creators had to halt production entirely and now they're stuck trying to scramble and find a new tech partner while they're at the festival. The whole thing is a feature-length animated movie about woodland creatures, and it actually started out back in 2023 as a short film made with DALL-E. The plan was pretty wild, they had 15 people trying to pull off a Pixar-style animation in just 9 months, which is crazy compared to the usual 3 years and 300 people it takes a big studio. The budget was sitting at $30 million, which is nothing compared to Hollywood's standard $200 million overhead. But then OpenAI completely scrapped their whole video division to push resources into robotics and coding models, which apparently even paused a $1 billion deal they had going with Disney. OpenAI is officially distancing themselves now, saying they aren't funding or producing the project and that the creators were just using their tools for a creative experiment. It really just shows how risky AI filmmaking is right now since you're totally dependent on external platforms. When a tech giant decides to just pull the plug on an expensive system, it completely derails the independent creative process. Source: [https://futurism.com/artificial-intelligence/openai-attempt-ai-pixar-movie-shambles](https://futurism.com/artificial-intelligence/openai-attempt-ai-pixar-movie-shambles)
OpenAI has launched Sora, its video generation technology, to the public with safety measures including C2PA metadata, watermarks, and safeguards against abuse. The system has known limitations in physics and complex actions but represents a significant advancement in AI-powered video creation capabilities.
OpenAI announces comprehensive safety measures for Sora 2 and the Sora app, including provenance signals, C2PA metadata embedding, consent-based likeness controls through characters, and enhanced protections for teen users. The approach combines technical safeguards like content filtering with policy-based guardrails to prevent misuse of AI-generated video.
OpenAI releases Sora System Card detailing safety mitigations and red teaming efforts for Sora, their text-to-video generation model capable of creating up to 1080p videos with 20-second duration. The document outlines pre-training filtering, external red teaming across nine countries testing 15,000+ generations, and safeguards against misuse of likeness and misleading content.
OpenAI announces safety-focused launch of Sora 2 and the Sora app with built-in protections including watermarking, C2PA metadata, consent-based likeness controls, teen safeguards, and multi-layered content filtering for harmful material and audio.