Loading video...

Video Failed to Load

Go Home

4/ Recursive Memory Attention Running self-attention via the kernel for processing hierarchical attention unreasonably fast Built in Rust and runs quickly noah

31,669 views • 1 year ago •via X (Twitter)

12 Comments

Alex Reibman 🖇️'s profile picture
Alex Reibman 🖇️1 year ago

Saw these guys walking around Hayes looking for coworking space, so I invited them to HQ I was not prepared. These guys are absolutely cracked. Here’s the demos from the Swedish Hack Mafia (🧵):

Alex Reibman 🖇️'s profile picture
Alex Reibman 🖇️1 year ago

1/ Lovable AI agent for building + replicating websites Agentic web app builder @lovable_dev

Alex Reibman 🖇️'s profile picture
Alex Reibman 🖇️1 year ago

2/ Rubik’s Cube CSS 3D interactive Rubik’s cube built entirely in CSS @whosmatu

Alex Reibman 🖇️'s profile picture
Alex Reibman 🖇️1 year ago

3/ ChatTree Visualize ChatGPT conversations as interactive trees @rikardradovac

Alex Reibman 🖇️'s profile picture
Alex Reibman 🖇️1 year ago

Are you also cracked and want to work on insane, ambitious projects? I’m hiring engineers to build the next generation Agent Stack, DM me @AlexReibman @AgentOpsAI

Alex Reibman 🖇️'s profile picture
Alex Reibman 🖇️1 year ago

5/ E.M.A.I.L. AI agent that autonomously scrapes websites and creates cold outreach emails @jameszhou02 (not actually Swedish)

Jordan Ross's profile picture
Jordan Ross1 year ago

The most successful agency owners remove themselves from client servicing so they can focus on growing the business. Here's how we help our clients do that:

Dhruv 👾's profile picture
Dhruv 👾1 year ago

@DonaldPepe1 Hey @DonaldPepe1 , is this open source? I would love to checkout your project.

DonnySolana's profile picture
DonnySolana1 year ago

@DonaldPepe1 nice.

∯🔔's profile picture
∯🔔1 year ago

@threadreaderapp unroll here

Thread Reader App's profile picture
Thread Reader App1 year ago

@AlexReibman @Thrasymachus5 Hola, here is your unroll: Talk to you soon. 🤖

Free's profile picture
Free1 year ago

@DonaldPepe1 Smart. Does it improve accuracy?

Related Videos

New short course: Attention in Transformers: Concepts and Code in PyTorch. Last week we released a course on how LLM transformers work. This week, go deeper and learn about the technical ideas behind the attention mechanism, and see how to code it in PyTorch. This course is built with Joshua Starmer, Founder and CEO of StatQuest. The attention mechanism was a breakthrough that led to transformers, the architecture powering large language models like ChatGPT. Transformers, introduced in the 2017 paper: "Attention is All You Need" by Viswani and others, took off because of its highly scalable design. In this course, you’ll learn how the attention mechanism, a key element of transformer-based LLMs, works and implement it in PyTorch. You'll develop deep intuition about building reliable, functional, and scalable AI applications. What you will do: - Understand the evolution of the attention mechanism, a key breakthrough that led to transformers. - Learn the relationships between word embeddings, positional embeddings, and attention. - Learn about the Query, Key, and Value matrices, and how to produce and use them in attention. - Walk through the math required to calculate self-attention and masked self-attention to learn why and how they work. - Understand the difference between self-attention and masked self-attention and how one is used in the encoder to build context-aware embeddings and the other is used in the decoder for generative outputs. - Learn the details of the encoder-decoder architecture, cross-attention, and multi-head attention and how they are all incorporated into a transformer. - Use PyTorch to code a class that implements self-attention, masked self-attention, and multi-head attention. There're lots of exciting technical details in this course. Please sign up here:

Andrew Ng

132,135 views • 1 year ago