Loading video...

Video Failed to Load

Go Home

“Chat with your PDF” still fails on ChatGPT/Claude when the doc is too complex 📉🧾 . If it’s a complicated financial report with scanned tables, you’re going to get back hallucinated values in your analysis! Check out the video 🎬 - in the first part, Claude gives back hallucinated...

21,369 views • 1 year ago •via X (Twitter)

13 Comments

Frank's profile picture
Frank1 year ago

Thanks Jerry. You shows what matters: precision parsing + structured indexing.

Mobile Scanner's profile picture
Mobile Scanner1 year ago

Scan any documents, convert images into text, PDF files, etc. 👍

MasterChief's profile picture
MasterChief1 year ago

What the solution?

Gunter🅧🌱's profile picture
Gunter🅧🌱1 year ago

@goodalexander

AI Expert Khalid's profile picture
AI Expert Khalid1 year ago

LlamaCloud's parsing powers are awesome! Makes those AI hallucinations a thing of the past. Thanks for sharing the tech treasure! 🎉📊

Tsukuyomi's profile picture
Tsukuyomi1 year ago

ah, the joys of AI hallucinations. makes you wonder if the real problem is the docs or the brains behind the bots. 🤔

Himanshu Kumar's profile picture
Himanshu Kumar1 year ago

Perhaps AI needs a deeper understanding before tackling nuanced documents.

Lou 🌲's profile picture
Lou 🌲1 year ago

Man this is what I've been looking for

Himanshu Srivastava's profile picture
Himanshu Srivastava1 year ago

Chatting with internal data is still a big pain point.

Andrej Karpathy's profile picture
Andrej Karpathy1 year ago

How to build a thriving open source community by writing code like bacteria do 🦠. Bacterial code (genomes) are: - small (each line of code costs energy) - modular (organized into groups of swappable operons) - self-contained (easily "copy paste-able" via horizontal gene transfer) If chunks of code are small, modular, self-contained and trivial to copy-and-paste, the community can thrive via horizontal gene transfer. For any function (gene) or class (operon) that you write: can you imagine someone going "yoink" without knowing the rest of your code or having to import anything new, to gain a benefit? Could your code be a trending GitHub gist? This coding style guide has allowed bacteria to colonize every ecological nook from cold to hot to acidic or alkaline in the depths of the Earth and the vacuum of space, along with an insane diversity of carbon anabolism, energy metabolism, etc. It excels at rapid prototyping but... it can't build complex life. By comparison, the eukaryotic genome is a significantly larger, more complex, organized and coupled monorepo. Significantly less inventive but necessary for complex life - for building entire organs and coordinating their activity. With our advantage of intelligent design, it should possible to take advantage of both. Build a eukaryotic monorepo backbone if you have to, but maximize bacterial DNA.

elvis's profile picture
elvis1 year ago

Agentic RAG for Personalized Recommendation This is a really good example of integrating agentic reasoning into RAG. Leads to better personalization and improved recommendations. Here are my notes:

alphaXiv's profile picture
alphaXiv1 year ago

potentially a new AI generation paradigm? "Energy-Based Transformers are Scalable Learners and Thinkers" proposes Energy-Based Transformers (EBT), a new AI model that repeatedly checks and improves its own predictions through learned energy minimization.

Bojan Tunguz's profile picture
Bojan Tunguz1 year ago

This really hits close to home for me. My whole career in tech was one big unsuccessful struggle to try to explain the distinction between these various modes of operation, and why you will fail miserably if you try to impose a single mindset for all of them.

Related Videos

Big moment for Postgres! AI coding tools have been surprisingly bad at writing Postgres code. Not because the models are dumb, but because of how they learned SQL in the first place. LLMs are trained on the internet, which is full of outdated Stack Overflow answers and quick-fix tutorials. So when you ask an AI to generate a schema, it gives you something that technically runs but misses decades of Postgres evolution, like: - No GENERATED ALWAYS AS IDENTITY (added in PG10) - No expression or partial indexes - No NULLS NOT DISTINCT (PG15) - Missing CHECK constraints and proper foreign keys - Generic naming that tells you nothing But this is actually a solvable problem. You can teach AI tools to write better Postgres by giving them access to the right documentation at inference time. This exact solution is actually implemented in the newly released pg-aiguide by Tiger Data - Creators of TimescaleDB, which is an open-source MCP server that provides coding tools access to 35 years of Postgres expertise. In a gist, the MCP server enables: - Semantic search over the official PostgreSQL manual (version-aware, so it knows PG14 vs PG17 differences) - Curated skills with opinionated best practices for schema design, indexing, and constraints. I ran an experiment with Claude Code to see how well this works, and worked with the team to put this together. Prompt: "Generate a schema for an e-commerce site twice, one with the MCP server disabled, one with it enabled. Finally, run an assessment to compare the generated schemas." The run with the MCP server led to: - 420% more indexes (including partial and expression indexes) - 235% more constraints - 60% more tables (proper normalization) - 11 automation functions and triggers - Modern PG17 patterns throughout The MCP-assisted schema had proper data integrity, performance optimizations baked in, and followed naming conventions that actually make sense in production. pg-aiguide works with Claude Code, Cursor, VS Code, and any MCP-compatible tool. It's free and fully open source. I have shared the repo in the replies!

Avi Chawla

187,048 views • 7 months ago