X-Ray Feed – A Chrome extension to visualize the Twitter/X algorithm

I got tired of guessing why my timeline looked the way it did, so I built a tool to reverse-engineer the "Heavy Ranker" logic in real-time.

It’s an MV3 extension that overlays the hidden weight of every post directly in the feed. It distinguishes between organic content ("Thunder" nodes) and AI-injected recommendations ("Phoenix" nodes) so you can actually distinguish following vs. algorithmic fill.

The scoring is based on a log10(Engagement) * 20 formula to visualize velocity. I originally built it just to clean up my own feed hygiene, but it turned out to be a pretty useful arbitrage tool, identifying "flops" (good topics from big accounts that failed due to structure) that are worth rewriting.

All the analysis happens locally in the browser. Would love to hear what you think about the scoring accuracy.

https://xrayfeed.deepwalker.xyz

better than openclaw but missing some features like browser tool, etc. Once they are added, it will be way more performant than openclaw. FTS5 is a great pick, well done.

RAG is broken when you have too much data.

Specifically when the document number reaches around 10k+, a phenomenon called "Semantic Collapse" occurs.

https://dho.stanford.edu/wp-content/uploads/Legal_RAG_Halluc...

So you're telling me rampancy ( https://www.halopedia.org/Rampancy ) is real.

> Specifically when the document number reaches around 10k+

Where are you getting this? just read the paper and not seeing it -- interested to learn more

The RAG GP used suffered from semantic collapse.

where does it say that + what does GP mean here?

It was a stupid joke, don't mind it, sorry.

Cant you make thresholds higher?

Hmm... I guess not, you might want all that data.

Super interesting topic. Learning a lot.

Gemini with Google search is RAG using all public data, and it isn't broken.

It's not tool use with natural language search queries? That's what I'd expect.

It's RAG via tool use, where the storage and retreival method is an implementation detail.

I'm not a huge fan of the term RAG though because if you squint almost all tool use could be considered RAG.

But if you stick with RAG being a form of "knowledge search" then I think Google search easily fits.

It is tool use with natural language search queries but going down a layer they are searched on a vector DB, very similar to RAG. Essentially Google RankBrain is the very far ancestor to RAG before compute and scaling.

connection overhead is way too much for modern world.

I personally think Wyoming will be the capital of startups, especially 30 N Gould Str is going to be the street of world's startups.

No no you simple minded USAmerican. It's obviously going to be Uruguay, its on it's way to transform from MonteVideo to MonteLLM /s

I'm not an american :)

>Europe just became a lower-cost extension of Silicon Valley.

Stay away from europe while you can.

Please use Ada / SPARK.

thanks for this checker, we also need HN alternative for EU only. As Europeans, I'm sure we can do this.

I really wish this existed so that HN could go back to being a tech community of nerds and builders. Somehow HN has become overrun with more and more urban monoculture euro-fetishists and actual Europeans in the last few years. I haven't seen a headline mentioning Rust or Lisp in days! That's how you know things have really gone downhill.

European HN could focus on its favorite topics of privacy paranoia, "what regulation can we make next?" and tech safetyism, while maybe real HN could go back to Bay Area tech esotericism and fun historical anecdotes.

oh man, I agree with what you are saying but EU is a joke.!

Is it really though? We have strong labour laws, consumer laws, antitrust laws, personal information laws and so on because the majority of us want it. We understand that this do not maximize growth, and consider that worth it. In fact, the most of us sees the current US administration as a very big joke.