DeepLearning.AI

New course alert! 🚨 Learn how to build agentic memory into your applications with LLMs as Operating Systems: Agent Memory, a course created in partnership with Letta and taught by its founders, Charles Packer and Sarah Wooders. This course explores solutions from the innovative MemGPT paper, showing you how to manage the LLM’s context window for efficient, persistent memory. You’ll explore Letta, an open-source framework designed to give LLM agents advanced reasoning and long-term memory capabilities. Build agents with self-editing memory, customize memory blocks, and even implement multi-agent collaboration. Enroll for free: https://hubs.la/Q02XmDBK0

Yesterday, we launched LLMs as Operating Systems: Agent Memory with Letta. LLMs have limited input space, so managing context is crucial to maintain speed and reduce costs. In the innovative MemGPT paper, its authors, including the course instructors introduced an LLM agent that uses persistent memory to select relevant information efficiently. Using Letta’s open-source framework, this course will show you how to implement MemGPT, adding long-term memory to your LLM agents. Enroll for free: https://hubs.la/Q02XwFzN0

Meet Cyrus, who’s using coding to improve diabetes management. Living with Type 1 Diabetes, he’s harnessing machine learning to turn complex data into clear insights, making life easier for himself and others. Want to bring AI-driven coding skills to your own projects? Enroll in #AIPythonforBeginners today! https://lnkd.in/ezbn6iwm

As shipping ports adopt autonomous vehicles, robotic cranes, and AI-assisted data management systems, U.S. labor unions protest rapid changes that may threaten their jobs. Ports around the world are boosting efficiency and lowering costs through automation. Are dockworkers right to worry about job security? Learn more in #TheBatch: https://hubs.la/Q02XsVpG0

🌍 On November 20th, 30 nonprofits will showcase how AI can tackle climate change during AI for Climate Matching Day! 🌱 Let’s come together to support these solutions and drive real impact: https://hubs.la/Q02XsV0f0 Tech To The Rescue Explore how you can use AI to be part of the solution when it comes to addressing challenges in areas like public health, climate change, and disaster management in the AI for Good Specialization! Learn more: https://hubs.la/Q02XsM1J0

Generative AI for Software Development is the latest skills certificate by DeepLearning.AI available on Coursera, and learners are loving it! Swipe through to read what some learners are saying! Start your own learning journey here: https://bit.ly/4gM17Pz

Anthropic launched API tools that enable its Claude Sonnet 3.5 model to operate desktop applications using natural language commands to perform tasks like opening apps, managing files, and even coding. The updated model shows improved performance on benchmarks and is coupled with a faster variant called Claude Haiku 3.5. However, Anthropic advises using a sandboxed environment for the experimental computer use capabilities to avoid security risks. Learn more in #TheBatch: https://hubs.la/Q02XsH4j0

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper "MemGPT: Towards LLMs as Operating Systems," its authors (which include Charles and Sarah) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database, summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning  - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system)  - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!  https://lnkd.in/gu2BgqJE

Join in the fun! Enroll for free in the #AIPythonforBeginners course series 👉 https://lnkd.in/ezbn6iwm

This week in The Batch, Andrew Ng discusses how bots, not generative AI, may be manipulating social media algorithms to amplify political content, impacting democratic processes. Plus: 🌐 Claude's new API controls desktop apps – with caution ⚓ Automation sparks conflict in U.S. ports 🤖 Can AI agents handle ML tasks? Read #TheBatch now: https://hubs.la/Q02Xd8vr0