Show HN: Watch fascism unfold in realtime – an AI-powered tracker

Hi HN, Wanted to share a project I made over the weekend - a real-time fascism tracker. The site fetches recent news from trusted sources, filters it for keywords related to fascism and the current US administration, and then sends it to GPT-4o for classification according to the 14 characteristics of fascism described by Dr. Lawrence Britt. With the rapid pace of news in the US, especially post-election, it’s hard to keep up. I built this site so you can quickly see important topics and draw parallels with similar historical events. Would love to hear your thoughts. - Ryan

Show HN: Watch fascism unfold in realtime – an AI-powered tracker
realtimefascism.com

Technically impressive, deeply sobering, and I'm going to stay away because by the end of 2020 I was barely able to sleep, and this is so much worse.

Slick design, I like it.

Could just be me but with characteristic-level severity levels it's not immediately clear to me if they're referring to like the categorical severity (e.g. "when labor power is suppressed that's a critical sign of encroaching fascism") or the present-day severity (e.g. "recent news points to there being critical levels of labor suppression happening right now").

I can suss out that it seems to be the present-day severity, but it wasn't intuitive (for me at least).

And how does your scale/algorithm work in terms of time-dependence? If there isn't any news indicating signs / intentions of labor suppression for a couple weeks then does that drop the severity level (both at the characteristic level and/or the overall level)?

Cool project at the very least for keeping track of recent alarming news. I hope we never have to find out how accurate your tracker really is...(Then again that opens up the can of worms of "when does fascism arrive?"...with the answer always being earlier in retrospect than predicted in present.)

Thanks! and this is actually one of the things on my list. Still noodling on how to do this effectively and efficiently, since I want it to follow my same process of filtering through gpt-4o, and running 10 years of data through that could cost me.

But yes love the idea : )

impressive! so much good journalism exists on substack. wondering what criteria you're using for allowed sources and if you'll expand to different journalists' substacks.