alt Hacker NewsI think what you're seeing is the probability of a particular signature or style of signature appearing on a particular style of cartoon, not an intent to sign.
Replies
ctippett • today at 12:28 AM
This. It's also while you'll sometimes get a mangled Getty Images watermark on some image generations, or a logo in the bottom left corner. If it's a prominent feature in the training dataset it'll show up, exactly how these models are supposed to work.
The 'bug' here is whatever post-processing step or system prompt is in place to steer the model away from doing this.
➕ show 2 replies
Muromec • today at 12:44 AM
Yes, but that's just the pixel generation layer. The harness or whatever infrastructure around could nudge it towards common sense.
I do many voice transcriptions. Many times I've had empty silence at the end of recordings transcribed as "Thank you" or even "Like and subscribe".