Why's this poorly written piece on top of HN?
Interesting, has this already been experimented?
Because they will be running inference using much smaller models than GPT 4.
Part 69
Adding a watermark to all AI generated images should be imperative.
How is this different from the colour chart idea? If we know how some actual KNOWN RGB pixels look in a particular setup, we can apply the same filter across the image. Right?
Why's this poorly written piece on top of HN?
Interesting, has this already been experimented?
Because they will be running inference using much smaller models than GPT 4.
Part 69
Adding a watermark to all AI generated images should be imperative.
How is this different from the colour chart idea? If we know how some actual KNOWN RGB pixels look in a particular setup, we can apply the same filter across the image. Right?