Thread

1. WithinReason · 1790430559 · focus · HN ↗

   This is getting tiring. Watermarking has no effect on model output quality when implemented correctly. It's somewhat like swapping a random RNG seed to the seed 42, and detecting what the seed was from a random sequence. The sequence generated from the seed 42 is just as random as any other seed. There couldn't be a quality difference. And yes, the output from an LLM is a conditional random sequence of tokens from a distribution determined by a model.

   1. odo1242 · 1790439280 · focus · HN ↗

      Well, one issue is that the output becomes predictable. So the agent isn’t exploring the full state space of possibilities, it’s exploring (arbitrarily chosen weighted half of state space).

Unofficial Hacker News client; not affiliated with Y Combinator.