Am I missing something? The article seems to suggest it works via hidden text characters. Has OpenAI never heard of pasting text into a utf8 notepad before?
Am I missing something? The article seems to suggest it works via hidden text characters. Has OpenAI never heard of pasting text into a utf8 notepad before?
As someone who fiddled with Stable Diffusion which also has optional invisible watermarks this is a good feature. It is so that AI training will avoid content marking itself as AI generated. If people want to hide that their content is AI generated then, sadly, it’s harder to detect.
Watermarking everything I digitally publish to keep my original content out of a training set.
Publishing a website full of de-watermarked AI slop to ruin future LLMs.
More info if you’re seriously considering it. https://codoraven.com/blog/ai/stable-diffusion-the-invisible-watermark-in-generated-images/
I don’t actually know if any model creators check for the watermark or not.
Arent there better methods to poison AI?
I have heard Glaze and Nightshade are good, but have never used them
They’re getting out of date already because newer models are catching up on them. It’s a cat and mouse game that will likely never end.