Sure but then they just train against that adversary too.
I think we do need to push for LLM generated content to be tagged or watermarked as such.
But we basically need ALL informational content to cite its sources.
Don't trust AND do verify.
I can't attend, but happening now:
cloudonair.withgoogle.com/events/conne...
"
Innovate with #GoogleCloud
Connect to #RemoteAgents with #ADK and #Agent2Agent SDK
Explore the Agent2Agent #A2A protocol, a solution for enabling generative AI agents to communicate and collaborate.
"
Connect to Remote Agents with ...