With Llama and local fine tuning, one can easily rephrase whatever gpt four says in the style of communication that I use on my emails; there really is no way to discover the watermark anymore. I think up to, I don’t know, a few hundred tokens or whatever. It’s been conclusively proved that it’s hopeless if you only have that short tokens. But if all you want to carry is a scamming conversation over sms, well, the token count is so low that there’s no way to watermark that.