it basically does a combination of: -- string text matching + embeddings

unfortunately there isn't a dashboard yet in the logged out view, but if you view the feed when logged into sprinklz you can directly see (and edit) all the params used

At its core, this isn’t merely a tool that navigates the complexities of the digital landscape—it’s a load-bearing solution that deliberately removes content generated using AI, rather than content about LLM models.

It’s worth noting that we’re not delving into the rich tapestry of discussions surrounding large language models themselves; instead, we’re underscoring the pivotal distinction between AI-generated material and authentic human writing about those very models. Ultimately, this approach fosters a more robust, seamless, and nuanced filtering process—one that leverages genuine insight rather than the multifaceted outputs of generative systems.

nice, yeah, I will keep working on it

I wanted to make this general purpose enough that it could handle large datasets (e.g. i want to do thiings like https://sprinklz.io/demo/headlineNews), so I was hesitant to do things like make 1-LLM-call-per-article, but I'll keep exploring ways to make it better

it isn't visible from this view, but it's designed so that you can edit the ranking params directly from your browser, e.g. https://sprinklz.io/demo/headlineNews or https://sprinklz.io/demo/codeEditor

You're still reading code like it's 2020? Wow