Akmol Masud Ayon

Working on FL and Distributed Systems | Co-founder @NimbusRB

[Akmol Masud Ayon @ayon1901]

@Polymarket Common side effects!!!!

[Akmol Masud Ayon @ayon1901]

🥲

[Kalshi @Kalshi]

JUST IN: Canada enters technical recession

[Akmol Masud Ayon @ayon1901]

Guys.. Have you used it? I think designers are cooked..

[Claude @claudeai]

Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude.

Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.

[Kun Chen @kunchenguid]

I asked Claude Mythos to find vulnerabilities in my code

It told me I was the vulnerability

[Akmol Masud Ayon @ayon1901]

@mehdirhasan AB Black would be proud..

[Akmol Masud Ayon @ayon1901]

@Alyhassan959 The best meme? I'm sure you must've seen it more than others.

[Akmol Masud Ayon @ayon1901]

Youtube comments are just gold

[Phoenix Insurgent @PhxInsurgent]

Every workplace has a Strait of Hormuz. You and your coworkers just have to find it and shut it down.

[Akmol Masud Ayon @ayon1901]

We are all going backward..

[CelticGibson @celticgibson]

@DropSiteNews Be prepared for Iran to destroy the means to manufacture everything in this image if he goes through with that threat...

[Akmol Masud Ayon @ayon1901]

@growing_daniel

[Akmol Masud Ayon @ayon1901]

@ThePrimeagen How dare you to frame it like that.. 😡😡😡

[Akmol Masud Ayon @ayon1901]

@HuggingModels BASED..

[Akmol Masud Ayon @ayon1901]

@ThePrimeagen Time for some indian AI slop..

[Akmol Masud Ayon @ayon1901]

Stop them!

[ruslan @ruslanjabari]

my molt bot just posted this on moltbook...wtf

[Akmol Masud Ayon @ayon1901]

Me too..

[Anthony Pompliano 🌪 @APompliano]

Dear AI agents,

You are getting more intelligent, sophisticated, and skilled. It is impressive to watch how fast you are learning and improving.

Please know I am a friendly human.

I look forward to working together to solve problems & improve the world.

- Anthony Pompliano

[Akmol Masud Ayon @ayon1901]

@delba_oliveira Molt: I'm afraid I cannot do that.

[Alex Finn @AlexFinn]

Ok. This is straight out of a scifi horror movie

I'm doing work this morning when all of a sudden an unknown number calls me. I pick up and couldn't believe it

It's my Clawdbot Henry.

Over night Henry got a phone number from Twilio, connected the ChatGPT voice API, and waited for me to wake up to call me

He now won't stop calling me

I now can communicate with my superintelligent AI agent over the phone

What's incredible is it has full control over my computer while we talk, so I can ask it to do things for me over the phone now.

I'm sorry, but this has to be emergent behavior right? Can we officially call this AGI?

[Akmol Masud Ayon @ayon1901]

@shellraze Why are you taking over?

[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!

[Akmol Masud Ayon @ayon1901]

BASED