ᛒᛚᚢᛖ 🍉

You should probably stay away from me.

[ᛒᛚᚢᛖ 🍉 @Azur_xx]

“…I could collect all the stars in the universe and they still wouldn’t shine as bright as your eyes…”

[Seleman @Eromosele6]

🚨 BREAKING 🚨

22 year Nigerian student, Isaac Satlat, was hijacked and killed through strangulation last night.

His Bolt car was found and his body some kilometers away in Moshongo, Attridgeville just outside Pretoria.

The hijackers were a male and a female.

There's a video evidence of the incident through the camera in the car.💔

Please Help Retweet until the culprits are caught 🙏

[gst @wearegst]

The newly passed Tax Administration Act contains several dangerous provisions that could easily be weaponized against Nigerians.

[Avi Chawla @_avichawla]

Researchers built a new RAG approach that:

- does not need a vector DB.
- does not embed data.
- involves no chunking.
- performs no similarity search.

And it hit 98.7% accuracy on a financial benchmark (SOTA).

Here's the core problem with RAG that this new approach solves:

Traditional RAG chunks documents, embeds them into vectors, and retrieves based on semantic similarity.

But similarity ≠ relevance.

When you ask "What were the debt trends in 2023?", a vector search returns chunks that look similar.

But the actual answer might be buried in some Appendix, referenced on some page, in a section that shares zero semantic overlap with your query.

Traditional RAG would likely never find it.

PageIndex (open-source) solves this.

Instead of chunking and embedding, PageIndex builds a hierarchical tree structure from your documents, like an intelligent table of contents.

Then it uses reasoning to traverse that tree.

For instance, the model doesn't ask: "What text looks similar to this query?"

Instead, it asks: "Based on this document's structure, where would a human expert look for this answer?"

That's a fundamentally different approach with:

- No arbitrary chunking that breaks context.
- No vector DB infrastructure to maintain.
- Traceable retrieval to see exactly why it chose a specific section.
- The ability to see in-document references ("see Table 5.3") the way a human would.

But here's the deeper issue that it solves.

Vector search treats every query as independent.

But documents have structure and logic, like sections that reference other sections and context that builds across pages.

PageIndex respects that structure instead of flattening it into embeddings.

Do note that this approach may not make sense in every use case since traditional vector search is still fast, simple, and works well for many applications.

But for professional documents that require domain expertise and multi-step reasoning, this tree-based, reasoning-first approach shines.

For instance, PageIndex achieved 98.7% accuracy on FinanceBench, significantly outperforming traditional vector-based RAG systems on complex financial document analysis.

Everything is fully open-source, so you can see the full implementation in GitHub and try it yourself.

I have shared the GitHub repo in the replies!

[gst @wearegst]

The money the government steals doesn’t disappear. It shows up as suffering, scarcity, and lives cut short.

[Joshua Neal @joshuaneall]

Dating is draining, dates aren't: "Part One"

[Rossini❤️🌹 @TwRossini]

I never do this but I need help
My baby brother needs a Total Hip Replacement surgery in March after his semester.
Cost is around ₦2.5M to ₦3M.
He is 18. Walking hurts him, makes school hard and I am starting a crowdfunding and I am asking for retweets, prayers and support!

[Zohran Kwame Mamdani @ZohranKMamdani]

Friends, I’m once again asking you to donate. But not to me!

@claireforny is a union organizer, democratic socialist and my former Assembly colleague running for Congress in NY-7. Chip in today.

[UpScrolled @realUpScrolled]

You’re noticing it too.
More people are showing up on UpScrolled.
Massive shoutout to everyone who’s already secured their handle and joined a platform that puts creators first.
Got your UpScrolled handle? Drop it below 👇
Don’t have one yet? Time to scroll differently.

[ᛒᛚᚢᛖ 🍉 @Azur_xx]

I need to someone to take the memory of this series away from me so I can witness peak again

[⟢ gaia @magdurugo]

GUYS . GUYS ……. my world is spinning i can’t do this MY STOMACHHHHH

[Siddharth @DearthOfSid]

Parenti on “free market” mythology.

The world has lost a great thinker whose clarity and courage shaped generations of left political thought.

[ᛒᛚᚢᛖ 🍉 @Azur_xx]

@turntineforwhat I will keep fighting the good fight

[Lizistrata🔻 🇵🇸 @Iysistrata]

Godspeed 🖤

[ᛒᛚᚢᛖ 🍉 @Azur_xx]

Nazi germany concluded that America was too racist

[ᛒᛚᚢᛖ 🍉 @Azur_xx]

I have written poems about people but I have learned that it’s better I face a raging bull than actually show them

[alex turntine @turntineforwhat]

bookmarking these instead of sending them to him, in order to maintain my air of mystery & nonchalance (I wrote him a poem and gave it to him the second time we hung out)

[Iwali 🦋✨ @IamIwali]

So hit me up if you want a kiss

[ᛒᛚᚢᛖ 🍉 @Azur_xx]

Bro

[Gele warrior 😝⭐️ @Doyinpepperr]

Omo who pay for kissing pr?😭

[Hansel Praise @hannytalker]

Applications are now open.

If you’re a woman looking to start or grow a career in Health, Safety and Environment, especially offshore or industrial HSE, this is an opportunity worth serious attention.

NEBOSH, in collaboration with L’Oréal, is running the NEBOSH L’Oréal International Bursary: Enabling Women in Health and Safety for the fourth year in a row. The programme offers a fully funded bursary for women outside the UK to study for the NEBOSH International General Certificate in Occupational Health and Safety.

What the bursary covers
• Full funding for the course and exams
• A globally recognised HSE qualification
• A real pathway to enter or progress in the HSE field

Who can apply
Women based outside the UK who are genuinely interested in building a career in health and safety.

Application deadline: 20 February 2026

Find full details and apply here:
👉 https://t.co/NlWNqPWAjV

[ᛒᛚᚢᛖ 🍉 @Azur_xx]

@partyjolloff You never see anything

[SHOW @SogbesanWariz]

I need a lady with a bachelor’s degree in Physics, Statistics, or Mechanical Engineering and she’s open to relocating to the UK.

please send a dm.

[ᛒᛚᚢᛖ 🍉 @Azur_xx]

GGMU ❤️