Dominic_P

I think that's totally true, but what I think will keep people with us is the global cache. Because it's constantly being updated by OSS users, we will always have an up-to-date view of the web's sitemaps. Would love to hear what you think.

My biggest question (maybe this has already been taken care of) is the issue of garbage in and garbage out. If the LLM produces bad content then that is used to train another model, how do we stop them from keeping their blindspots across models?