Scott Aaronson, while working at OpenAI, largely solved AI text watermarking together with Hendrik Kirchner. Here is how his solution works, or see Tenobrus’s version . AI outputs are not deterministic. The AI’s job is to pick the probability of each potential next token. The token is then chosen at random. By default you use a source of pseudo-randomness for each choice, since actual true…
Comments
Nothing yet. Say the first thing.
Sign in to join the conversation.