Inexpensive token generation and agentic workflows for large language models (LLMs) open up intriguing new possibilities for training LLMs on synthetic data. Pretraining an LLM on its own directly generated responses to prompts doesn't help. But if an agentic workflow implemented…

Chatting with Groq Inc’s CEO Jonathan Ross. Groq has super fast token generation capabilities now. And, I was excited also to hear about his plans to scale up capacity aggressively and also expand this to other models than just LLMs! This is a good time to be building AI…

In Prompt Engineering for Vision Models, taught by Abby Jacques Verre and Caleb Kaiser of Comet , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for…

I've really enjoyed using crewAI 's tools to build multiagent AI systems -- in addition to being productive, it's also fun to use! It was great hanging out with its creator João Moura to chat about best practices for building agentic workflows.

Much has been said about many companies’ desire for more compute (as well as data) to train larger foundation models. I think it’s under-appreciated that we have nowhere near enough compute available for inference on foundation models as well.

Years ago, when I was leading teams…

New short course with Mistral AI !

Mistral's open-source Mixtral 8x7B model uses a 'mixture of experts' (MoE) architecture. Unlike a standard transformer, an MoE model has multiple expert feed-forward networks (8 in this case), with a gating network selecting two experts at…

Meta released Llama 3 on my birthday! 🎂 Best present ever, thanks Meta! 😀

Multi-agent collaboration has emerged as a key AI agentic design pattern. Given a complex task like writing software, a multi-agent approach would break down the task into subtasks to be executed by different roles -- such as a software engineer, product manager, designer, QA…

LLMs can take gigabytes of memory to store, which limits what can be run on consumer hardware. But quantization can dramatically compress models, making a wider selection of models available to developers. You can often reduce model size by 4x or more while maintaining reasonable…

Planning is a key agentic AI design pattern in which we use a large language model (LLM) to autonomously decide on what sequence of steps to execute to accomplish a larger task. For example, if we ask an agent to do online research on a given topic, we might use an LLM to break…

Data preprocessing is critical for building effective RAG systems. Our new short course, Preprocessing Unstructured Data for LLM Applications, taught by Matt Robinson of UnstructuredIO, demonstrates important but sometimes overlooked aspects of RAG systems:

- How to extract…

The Financial Times has a great article on Renate Nyborg Renate Nyborg's work on Meeno , written by Madhumita Murgia.

The article is paywalled, but I appreciate Renate (as well as Harvard's Ron Ivey)'s leadership speaking about the dangers of the AI fake girlfriend/boyfriend…

The task-based analysis of how AI affects jobs is a powerful technique for creating business value. It was pioneered by Workhelix’s Erik Brynjolfsson et al. Now, Workhelix has developed technology to apply this at scale, by automatically examining a company’s job descriptions,…

Tool use, in which an LLM is given functions it can request to call for gathering information, taking action, or manipulating data, is a key design pattern of AI agentic workflows. You may be familiar with LLM-based systems that can perform a web search or execute code. Some of…

Learn to carry out red teaming attacks against your own LLM-based applications to spot and patch vulnerabilities! In our new short course, Red Teaming LLM Applications, Matteo Dora & Luca Martial of LLM testing company Giskard teach how to simulate malicious actions to…

I hope everyone in Taiwan 🇹🇼 is okay after the earthquake. My thoughts are with everyone affected. ❤️

Last week, I described four design patterns for AI agentic workflows that I believe will drive significant progress this year: Reflection, Tool use, Planning and Multi-agent collaboration. Instead of having an LLM generate its final output directly, an agentic workflow prompts…

New JavaScript short course: Build a full-stack web application that uses RAG in JavaScript RAG Web Apps with LlamaIndex, taught by Laurie Voss, VP of Developer Relations at LlamaIndex 🦙 and npm co-founder.
- Build a RAG application for querying your own data
- Develop tools to…