My mind is blown.

Groq Inc is serving LLaMA 3 at over 800 tokens per second!

800. Tokens. Per. Second.

This unlocks so many incredible use-cases.

It's one thing to see my demo — it's another thing entirely to experience it for yourself.

Do yourself a favor and try it asap.

Excited to introduce a new project I've been working on called Payman!

Payman is an AI Agent tool that gives Agents the ability to pay people for tasks they cannot do themselves.

While many people imagine a future where humans pay AI agents for services they want completed,…

Interesting strategy on how to turn your document into a knowledge graph

Fine-Tuning Is Typically A Bad Idea

There is a lot of misinformation in the market, and companies often ask for a 'custom model,' their own LLM, or want to fine-tune an LLM

Unless you need a very specific type of output/task - for example, a particular type of equation or some…

Building and evaluating RAG applications can get difficult! Thanks for having me on Mayo Oshin to share how we are helping with that at LastMile AI

Install our Visual Studio Code extension to get started: marketplace.visualstudio.com/items?itemName…

One of the major challenges with building AI chatbot applications is figuring out the optimal prompts and models for your use case.

Managing and evaluating multiple prompts alongside the RAG system can be tedious and complex.

Fortunately, LastMile AI provides a FREE notebook…

Is RAG Really Dead? Testing the retrieval limits of long context LLMs

RAG systems often retrieve multiple docs relevant to a user input and reason over them to return an answer.

How well can long context LLMs do this across hundreds or thousands of pages of input tokens?…

Today we're excited to introduce Devin, the first AI software engineer.

Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork.

Devin is…

One of the major challenges with launching AI-powered chat apps is monitoring how well it performs and understanding how users interact with it.

Most teams resort to manual evaluation and ad hoc testing of performance which is tedious, expensive, and leads to poor user…

Datasets for LLMs

A comprehensive overview (180+ pages) and analysis of LLM datasets.

I’ve talked about how a big step towards better RAG, no matter what downstream model you’re using (GPT-4, Mistral, Gemini 1.5 Pro, etc.) is to just have a really nice PDF parser.

It’s so important because a good parser unlocks way more interesting indexing/retrieval strategies…

There is a huge gap in generative AI between the quality you observe when you're playing with it open endedly, and the quality you observe when you try to use it for a task where you have a specific end goal in mind. This is I think where most of the hype/reality mismatch occurs.

Today I have a huge announcement.

The dataset used to create Open Hermes 2.5 and Nous-Hermes 2 is now PUBLIC!

Available Here: huggingface.co/datasets/tekni…

This dataset was the culmination of all my work on curating, filtering, and generating datasets, with over 1M Examples from…

Harsh truths to get you disillusioned before you waste your life:

- Product Hunt is useless BS ego play in the indie hacker echo chambers. If you need to impress your friends, hit the gym.

- Building an audience is great for your mom, not so great for your bottom line.

-…

📰 Top AI tools featured in the latest 'Chat with Data' newsletter

- Vanna AI: An open source 'Chat with Database' framework by Zain Hoda

- GPT-Newspaper: Create your own curated newspaper with AI [link: t.ly/EHOuD]

- PdftoChat: A free privacy-focused AI…