AIGuys Digest | Oct 2024

🌟 Welcome to the AIGuys Digest Newsletter, where we cover State-of-the-Art AI breakthroughs and all the major AI news🚀.

Don’t forget to check my new book on AI, it covers a lot of AI optimizations and hands-on code:

Ultimate Neural Network Programming with Python

🔍 Inside this Issue:

• 🤖 Latest Breakthroughs: This month it’s all about Scaling RAGs for Production, The Prompt Report, and LLM's black box nature.
• 🌐 AI Monthly News: Discover how these stories revolutionize industries and impact everyday life: AI Scientists winning the Noble Prize in Chemistry and Physics, OpenAI challenges Google Search and Big Tech makes big money.
• 📚 Editor’s Special: This covers the interesting talks, lectures, and articles we came across recently.

Let’s embark on this journey of discovery together! 🚀🤖🌟

Follow me on Twitter and LinkedIn at RealAIGuys and AIGuysEditor.

Latest Breakthroughs

This article covers different issues with creating a production-grade RAG system, understanding the deterministic nature of processes, and delving deep into the advanced RAG components. We will cover everything from reranker to repacking, from query classification to query expansion and many more such techniques that form the backbone of a modern RAG system.

Why Scaling RAGs For Production Is So Hard?

Don’t worry I’m not going to give you a list of the top 50 prompts to try, anyways that just doesn’t work at scale. We are here going to talk about different prompting techniques.

The Six Major Prompting Categories

Within the 58 categories, there are 6 top-level categories.

1. Zero-Shot
2. Few-Shot
3. Thought Generation
4. Decomposition
5. Ensembling
6. Self-Criticism

The Prompt Report: Prompt Engineering Techniques

A brand new paper from Google and Apple, where they looked into the internal LLMs to understand the nature of hallucinations. They showed that internal representations can also be used for predicting the types of errors the model is likely to make, facilitating the development of tailored mitigation strategies.

They also reveal a discrepancy between LLMs’ internal encoding and external behavior: they may encode the correct answer, yet consistently generate an incorrect one. Taken together, these insights deepen our understanding of LLM errors from the model’s internal perspective, which can guide future research on enhancing error analysis and mitigation.

LLMs Know More Than They Show

Apple says: “we found no evidence of formal reasoning in language models …. Their behavior is better explained by sophisticated pattern matching — so fragile, in fact, that changing names can alter results by ~10%!”

Apple Says LLMs Are Really Not That Smart

AI Monthly News

Computer Scientists Wins Noble In Both Physics and Chemistry.

This year’s two Nobel Laureates in Physics have used tools from physics to develop methods that are the foundation of today’s powerful machine learning. John Hopfield created an associative memory that can store and reconstruct images and other types of patterns in data. Geoffrey Hinton invented a method that can autonomously find properties in data, and so perform tasks such as identifying specific elements in pictures.

Press release: Click here

The Nobel Prize in Chemistry 2024 is about pro­teins, life’s ingenious chemical tools. David Baker has succeeded with the almost impossible feat of building entirely new kinds of proteins. Demis Hassabis and John Jumper have developed an AI model to solve a 50-year-old problem: predicting proteins’ complex structures. These discoveries hold enormous potential.

Press release: Click here

OpenAI Challenges Google’s Search Monopoly

OpenAI has introduced a search capability within ChatGPT, enabling real-time web browsing to provide up-to-date information. This feature positions ChatGPT as a direct competitor to traditional search engines like Google.

News Article: Click here

Big Tech Makes Big Money

Elon Musk’s xAI Seeks $40 Billion Valuation: Elon Musk’s AI startup, xAI, is in talks to raise funding at a valuation of $40 billion, up from $24 billion five months prior. The company is developing an AI chatbot named Grok, available on Musk’s social media platform X.

News Article: Click here

Both Microsoft’s and Google’s AI-driven investment leads to a profit surge:

Microsoft’s substantial investments in AI have resulted in a 16% increase in quarterly sales, reaching $65.6 billion. The Azure cloud computing division saw a 33% revenue rise, highlighting the impact of AI on business processes.

Google’s parent company, reported a 34% increase in profit, earning $26.3 billion in the July-September quarter. This growth is attributed to AI investments and a 15% revenue surge to $88.27 billion

News Article: Click here

News Article: Click here

Editor’s Special

• The Elegant Math Behind Machine Learning Click here
• AI RISING: Risk vs Reward — The Hinton Lectures™: Click here
• A fireside chat with Sam Altman OpenAI CEO at Harvard University: Click here
• NVIDIA’s New Ray Tracing Tech Should Be Impossible!: Click here

🤝 Join the Conversation: Your thoughts and insights are valuable to us. Share your perspectives, and let’s build a community where knowledge and ideas flow freely. Follow us on Twitter and LinkedIn at RealAIGuys and AIGuysEditor.

Thank you for being part of the AIGuys community. Together, we’re not just observing the AI revolution; we’re part of it. Until next time, keep pushing the boundaries of what’s possible. 🚀🌟

Your AIGuys Digest Team