this means we are going to get o3 level open source models in a few months. So exciting !

This is how you do "Open" AI.

I don't see how OpenAI isn't cooked. Every single foundation model they have is under attack by open source.

Dall-E has Stable Diffusion and Flux.

Sora has Tencent's Hunyuan, Nvidia's Cosmos, LTX-1, Mochi, CogVideo.

GPT has Llama.

o1 has R1.

And like with R1, these are all extensible, fine tunable, programmable. They're getting huge ecosystems built up around them.

In the image/video space there are ComfyUI, ControlNets, HuggingFace finetrainers, LoRAs. People share weights and training data.

Open source is so much better to base a company on than a proprietary model and API.

...

It looks there is no moat.