I am tasking grok bot to scan articles in regional languages around the world to detect unusual messaging. Hopefully I can be a bit more alert to what someone somewhere really wants me to believe. It will probably take some fine-tuning.
Login to reply
Replies (1)
Yeah. Seems LLMs would be good for that, it'd be tuning the summary bubbles, maybe k means squared type of clustering problem, so not so difficult with how well LLMs can do semantics (I gather). Evolution of the "axes" or bubble topics over time would be a simple enough chart too.
Make it so