Editorial illustration for Researchers say OpenAI's Sora and Google's Veo aren't true world models
OpenAI Sora & Google Veo: Not True World Models Yet
Everyone got drunk on the same idea. OpenAI released Sora, and the tech press instantly crowned it a "world simulator." Google's Demis Hassabis said the same about Veo. The promise was a machine that grasped how things actually work. A new paper says that's nonsense.
The researchers state it plainly. Sora and Veo are not world models. They side with Yann LeCun.
These tools can render a convincing splash of water or a car making a turn. That's mimicry. A real world model must perceive an environment and interact with it.
Text-to-video does neither. It generates from a prompt, not from sensory input. It has no feedback.
The paper is clear: this work falls "outside the core tasks of world models." The distance between a pretty animation and a model that understands the world is vast.
When OpenAI rolled out its now-discontinued Sora video model, plenty of people called it a "world simulator." Deepmind CEO Demis Hassabis made similar claims about Google's Veo video model, positioning it as a step toward world models. The authors flat-out disagree, landing on the same side as Yann LeCun: while video generation shows some grasp of physical relationships, it's missing the crucial feedback loop with the real world. A model that only generates videos from text doesn't perceive its environment and doesn't interact with it. Text-to-video therefore falls "outside the core tasks of world models," the paper states.
This is the core failure. Real understanding requires consequence. You learn by bumping into a wall, by feeling resistance, by failing.
A video model just guesses the next plausible pixel. It never touches anything. It has no skin in the game.
Calling it a world model is more than hype. It confuses a reflection for the thing itself, and muddies what building real intelligence actually requires.
Related Reading
Browse all OpenAI news →
Research & Benchmarks Google's FACTS benchmark shows 70% factuality ceiling across four tests
Research & Benchmarks Databricks finds multi-step agents beat single-turn RAG by 21% to 38% on STaRK
Research & Benchmarks Nvidia's DLSS 4.5 beta adds 6x Multi Frame Generation for RTX 50 GPUs
Related Topic OpenAI researcher quits, citing distrust over ad‑driven engagement metrics
LLMs & Generative AI
Related Topic OpenAI launches GPT-Image 1.5 with precise editing for enterprise visuals
LLMs & Generative AI
From Archives TriAttention KV Cache Compression Matches Full Attention, 2.5× Faster
From Archives Knowledge Distillation Keeps Student Model Capacity to Match Ensemble Boundaries
From Archives Cursor, Windsurf get funding for tools; OpenAI, Google, Anthropic add products
AI Tools & Apps
From Archives Stalking victim sues OpenAI, says ChatGPT fed ex’s delusions, hid safety info
LLMs & Generative AI
Common Questions Answered
Why do researchers argue that Sora and Veo are not true world models?
Researchers argue that Sora and Veo lack a crucial feedback loop with the real world, which is essential for true world modeling. These AI systems generate videos from text prompts but cannot interact with or learn from an actual environment, failing to meet the key criteria of perception, interaction, and memory.
What specific criteria do researchers use to define a world model?
The researchers outline a framework that requires three key elements: perception, interaction, and memory. Current text-to-video AI systems like Sora and Veo can only generate videos from prompts, but cannot receive sensory feedback, interact with an environment, or retain episodic memory beyond the generated clip.
How do prominent AI researchers like Yann LeCun view current text-to-video AI models?
Yann LeCun and other researchers are skeptical of claims that current text-to-video AI models are true world simulators. While these models show some understanding of physical relationships, they fundamentally lack the ability to learn and interact with the real world in a meaningful way.
Further Reading
- Veo-2 vs Sora: What Google Has (That OpenAI Doesn't) — Themesis
- OpenAI Sora 2 Team: How Generative Video Will Unlock Creativity and World Models — Sequoia Capital
- Google Veo 3 Explained: How It Stacks Up Against OpenAI's Sora — IAmDave.ai
- OpenAI's Sora video generator beats Google's Veo 3 by removing ... — Android Central
