OpenAI reveals DALL-E, a 12-billion-parameter version of GPT-3 trained to generate images from text descriptions. Type 'an armchair in the shape of an avocado' and get a photorealistic image back. It is not released to the public, but the concept is proven: language can direct visual creation. For creators, this is the 'holy grail' moment. The idea that you could describe what you want and have AI create it transitions from science fiction to demonstrated reality. Everything that follows in AI video builds on this foundation.