GPT-6 Astra vs Opus 5.5: same-prompt video comparison
A clip-by-clip comparison of videos generated by GPT-6 Astra and Opus 5.5 from the same prompt, with the author noting he can no longer tell which clips are AI-made.
It is becoming f*cking dangerous. GPT-6 Astra vs Opus 5.5, same prompt, every clip. A shark out of a persian rug. A warship swallowed by a wave. One row is AI, and so is the other. Six months ago you caught the fake in a second: the hands, the physics, the melt. Now I’m staring at my own renders trying to remember which ones I made. The deepfake problem everyone called years away is now one sentence typed into a laptop. So forget who won, the real question is what happens when no clip can be trusted again. And we’re already there. I run one of these every week. staying ahead of it is starting to feel less optional than it used to.
This post quotes another post: x.com/kinderlayer/status/2109997714591068522