Join MongoDB's AI Dev Quest

How are you, @e3e77916db?

🪐 What’s happening in tech today, June 27, 2024?

The HackerNoon Newsletter brings the HackerNoon homepage straight to your inbox. On this day, Nolan Bushnell and Ted Dabney Founded Atari in 1972, Telegraph Wires Connected New York and Boston in 1847 , Spyglass Went Public in 1995, The German Army Introduced the Enigma Machine in 1940, NASA's Mars Phoenix Spacecraft Landed on the Red Planet in 2008, The First Operational ATM in the World Opened in 1967, and we present you with these top quality stories. From The Open-Source Libraries to Check Out for LLM Building to How Vectors, Rag and Llama 3 Are Changing First-Party Data, let’s dive right in.

How to Build a Web Page Summarization App With Next.js, OpenAI, LangChain, and Supabase

TL;DR An app that can understand the context of any web page. Well show you how to create a handy web app that can summarize the content of any web page

By @nassermaronie [ 13 Min read ]

Our app will let users enter any website URL and quickly get a brief summary of the page. This means you can understand the main points of long articles, blog posts, or research papers without reading them fully.

Before we start, make sure you have the following:

https://github.com/firstpersoncode/summarize-page..

How Vectors, Rag and Llama 3 Are Changing First-Party Data

TL;DR In the battle for the best data, is first-party better? Not by itself, but it could be with vectors, frameworks like RAG, and open-source models

By @danielsvonava [ 6 Min read ]

First-Party Data is Back … With a Little Help From Its Friends. How Vectors, RAG and LLAMA 3 Are Driving a Sea Change

While these problems seem serious, is it time to give up on the potential– and the need for– first-party data? No way!

..

The Open-Source Libraries to Check Out for LLM Building

TL;DR This article presents some of the best libraries available for LLM development, categorized by their specific roles in the project lifecycle.

By @chawlaavi [ 10 Min read ]

GPT-2 (XL) has 1.5 billion parameters, and its parameters consume ~3GB of memory in 16-bit precision.

However, one can hardly train it on a single GPU with 30GB of memory.

That’s 10x the model’s memory, and you might wonder how that could be even possible.

Training and Scaling..

Should You Invest in Nvidia?

TL;DR Here are some of the arguments for and against investing in the company.

By @sheharyarkhan [ 5 Min read ]

Nvidia's done it! Nvidia's become a company worth $3 trillion! And it only took the company a little over three months to do so.

"Nvidia will decelerate," Barry Bannister, chief equity strategist at Stifel, was quoted as saying by the FT...

🧑‍💻 What happened in your world this week?

It's been said that writing can help consolidate technical knowledge, establish credibility, and contribute to emerging community standards. Feeling stuck? We got you covered ⬇️⬇️⬇️

We hope you enjoy this 34 minutes worth of free reading material. Feel free to forward this email to a nerdy friend who'll love you for it.

See you on Planet Internet! With love,

The HackerNoon Team ✌️