Claude next Model is scary I can say its over for image/video generation Everything you see is code it made from scratch the sound the images are code not web search, just pure javascript code We are not ready

Just wait until its distilled by china then it get’s really scary

Lol waiting that

Is this a image/video model? Or is it something different?

Just code

opus 5.5 is already absurd on audio visual, its incredible how they are managing to insert "taste" and the ability to "understand" almost indescribable stuff on these models like "vibes" etc..

It’s been proven numerous times that the models that don’t have image/video creation take so much longer in token costs, time, and money compared to a model that has image/video. There is definitely a bad side of JS, which you aren’t aware of.

Wow

Then we can officially say RIP to OpenAI

"its over" gets said every week lol. code generated visuals are cool but can it do the same thing twice in a row? thats the real test

Calling a model scary because its sound and images are pure JavaScript is a very 2026 way to be impressed by a demo.

Can you share the JS? I want to try moving the camera behind the dish and see what the scene looks like from there.

代码生成图像视频这条路确实在提速，不过离取代专用模型还有段距离，先让子弹飞一会

🥱

先别急着结束时代，让我看看跑起来有多卡

💀

If the whole video is just JavaScript, does that mean I can open dev tools and remix it like a webpage?

👀

作为天天写代码的程序员反而有点安心--它生成的视频声音都是 JavaScript，说明底层的生成机制离"黑盒魔法"又近了一步。日常写代码时用 AI 辅助已经离不开，看到这种纯代码合成音视频的方式，感觉接下来前端和创意工作流要被重新定义，有点兴奋也有点紧张。

💀💀💀

It has to generate faces too 😀

i would'nt say this is the end for image/video generation, this could very well be complementary

写了十年 iOS，头一回感觉自己像在手工打铁

Can you let me know how you generate these? What prompt?

Self recursive loop is cooking

The audio is the part that gets me. Canvas visuals from code are doable, but synth sound from code that doesn't feel like a 90s ringtone is much harder.