On: Understanding the Impact of LLM Watermarking on AI Agent Behavior

[possibilistic]

The comments here are orthogonal to what everyone should be talking about.

This is a spy tool.

It's not "watermarking", it's "spymarking": https://news.ycombinator.com/item?id=49794615

[cubefox → possibilistic]

A watermark is not a spy tool when it doesn't encode personal information.

[sodapopcan → cubefox]

The linked article explains this. Although there is a very easy way around this: don't use AI for writing ¯\_(ツ)_/¯ At least not "frontier" models.

[cubefox → sodapopcan]

This? The linked article explains what?