This doesn't change the temperature of the model. It's not going to make something that's a 70% chance suddenly a 100% chance. It also doesn't change the context length. At most, it seems like it may reduce some of the variation between different requests sampled from the same prompt with nonzero temperature, if I'm reading this right from the Google paper that Anthropic says they're implementing:
> For our experiments, we configure SynthID-Text to be single-sequence non-distortionary; this preserves text quality and provides good detectability, while having some reduction to inter-response diversity. We call this configuration ‘non-distortionary SynthID-Text’ (and where not otherwise specified, ‘SynthID-Text’ also refers to this).
That approach is pretty much what I was describing. The example in the paper uses the previous 4 tokens to derive the bias for the next token, so some 5 token sequences become more likely and others becomes less likely compared to what the LLM would normally produce. The context and temperature of the LLM stays the same, but the sampling process is biased by something that depends on far shorter runs of text.
> For our experiments, we configure SynthID-Text to be single-sequence non-distortionary; this preserves text quality and provides good detectability, while having some reduction to inter-response diversity. We call this configuration ‘non-distortionary SynthID-Text’ (and where not otherwise specified, ‘SynthID-Text’ also refers to this).
https://www.nature.com/articles/s41586-024-08025-4