It's not. They've mentioned that they had SynthID integrated before (I'm almost certain it was from the very start). What changed is that tools to detect that something is from Google's LLM is public now.
> Google has already integrated this new watermarking system into its Gemini chatbot, the company announced today.
Key word: already
> It has also open-sourced the tool and made it available to developers and businesses, allowing them to use the tool to determine whether text outputs have come from their own large language models (LLMs), the AI systems that power chatbots.
Is that not at odds with what's presented in the article here?