top of page

AI Technical Papers & Videos

This web page showcases the most impactful research papers and lectures that define the field of Artificial Intelligence (AI) and its diverse uses. It features pioneering thought leaders at the forefront, actively shaping and influencing the evolution of AI architectures and designs. 

Transformer: A Novel Neural Network Architecture for Language Understanding

In this seminal paper, researchers discovered that the "Transformer", an artificial intelligence model, was superior to other models in translating academic English to German and French. This model excels because of its strong natural language understanding capabilities, which means it's really good at interpreting and making sense of human language. It doesn't just translate better, but it also learns faster and is more compatible with modern computer systems. This compatibility makes the learning process up to ten times faster.

 

Read More

Large Language Models (LLMs) & SQL 

In this paper, Francisco Ingham and Jon Luo are two of the LangChain community members leading the change in SQL integrations.   This paper discusses applying large language models (LLMs) in interacting with SQL databases using natural language. It emphasizes the importance of SQL databases in storing enterprise data and the rising popularity of business intelligence tools for data querying and understanding. The paper also explores the potential of LLMs to understand and write SQL effectively while highlighting the challenges that make it a complex task. 

 

Read More

Hugging GPT

HuggingGPT is a new AI system that uses large language models, like ChatGPT, as a sort of "manager" to coordinate various other AI models to tackle complex tasks. The system leverages ChatGPT's language abilities to plan tasks, choose the right models for the job, execute the tasks, and summarize the results. By using this approach and accessing a wide range of AI models through Hugging Face, HuggingGPT can handle complex tasks across various fields such as language, vision, and speech, pushing the boundaries of advanced artificial intelligence.

​

Read More

🤗 Open Source LLM Leaderboard

With the plethora of large language models (LLMs) and chatbots being released week upon week, often with grandiose claims of their performance, it can be hard to filter out the genuine progress that is being made by the open-source community and which model is the current state of the art. The 🤗 Open LLM Leaderboard aims to track, rank and evaluate LLMs and chatbots as they are released. 

​

Read More

Inside language models (from GPT-4 to PaLM)

Dr Alan D. Thompson, a world expert in artificial intelligence (AI), specializes in augmenting human intelligence and advancing the evolution of integrated AI. His website is https://lifearchitect.ai/.  Alan dives deep into explaining LLMs and their various capabilities in this article.

​

Read More

GPT-4 - How does it work, and how do I build apps with it? - Harvard CS50 Tech Talk

In this lecture, Ted Benson, founder of Steamship, MIT Ph.D., & Y Combinator Alum; and Sil Hamilton, researcher of emergent AI behavior at McGill University,  discuss how GPT-4 works and why human language turns out to play such a critical role in computing. In addition, they discuss how AI-native software is being created.

*** This is CS50, Harvard University's introduction to the intellectual enterprises of computer science and the art of programming.

​

Watch Video

LLM Bootcamp - Spring 2023

In this series of lectures, speakers introduce attendees to building applications powered by large language models like GPT-4. Videos were recorded during the Full Stack Large Language Models Bootcamp on April 21, 2023 - April 22, 2023 in San Francisco.

​

Watch Video

Generative AI could raise global GDP by 7%

Breakthroughs in generative artificial intelligence have the potential to bring about sweeping changes to the global economy, according to Goldman Sachs Research. As tools using advances in natural language processing work their way into businesses and society, they could drive a 7% (or almost $7 trillion) increase in global GDP and lift productivity growth by 1.5 percentage points over a 10-year period.

​

Read Paper

bottom of page