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
@andrewyng
-
Data Preprocessing for RAG Systems and LLM Applications
By
–
Data preprocessing is critical for building effective RAG systems. Our new short course, Preprocessing Unstructured Data for LLM Applications, taught by @mrobinson0623 of @UnstructuredIO, demonstrates important but sometimes overlooked aspects of RAG systems:
— Andrew Ng (@AndrewYNg) 10 avril 2024
– How to extract… pic.twitter.com/mfhHoc2QfZData preprocessing is critical for building effective RAG systems. Our new short course, Preprocessing Unstructured Data for LLM Applications, taught by @mrobinson0623 of @UnstructuredIO
, demonstrates important but sometimes overlooked aspects of RAG systems: – How to extract -
AI Fake Girlfriend Dangers: Leadership Warning
By
–
The Financial Times has a great article on Renate Nyborg @renate
's work on @meeno_official , written by @madhumita29
. The article is paywalled, but I appreciate Renate (as well as Harvard's @ronivey
)'s leadership speaking about the dangers of the AI fake girlfriend/boyfriend -
AI Task Analysis Automates Job Impact Assessment at Scale
By
–
The task-based analysis of how AI affects jobs is a powerful technique for creating business value. It was pioneered by Workhelix’s @erikbryn et al. Now, Workhelix has developed technology to apply this at scale, by automatically examining a company’s job descriptions,
-
Tool Use in LLM-Based Agentic Workflows
By
–
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
-
Red Teaming LLM Applications: Securing AI Systems
By
–
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_ai teach how to simulate malicious actions to… pic.twitter.com/4S1PofwjhQ
— Andrew Ng (@AndrewYNg) 3 avril 2024Learn 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_ai teach how to simulate malicious actions to
-
Four Design Patterns for AI Agentic Workflows Driving Progress
By
–
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
-
JavaScript RAG Course: Build Full-Stack Web Apps with LlamaIndex
By
–
New JavaScript short course: Build a full-stack web application that uses RAG in JavaScript RAG Web Apps with LlamaIndex, taught by @seldo, VP of Developer Relations at @llama_index and npm co-founder.
— Andrew Ng (@AndrewYNg) 27 mars 2024
– Build a RAG application for querying your own data
– Develop tools to… pic.twitter.com/JB95PSQqtLNew JavaScript short course: Build a full-stack web application that uses RAG in JavaScript RAG Web Apps with LlamaIndex, taught by @seldo
, VP of Developer Relations at @llama_index and npm co-founder.
– Build a RAG application for querying your own data
– Develop tools to -
PyAutoGen Framework Leaders Discuss Multiagent Agent Design Patterns
By
–
I’ve been a fan of
@pyautogen
as a multiagent programming framework for awhile. It was great hosting two of its leaders
@Chi_Wang_
and
@qingyun_wu
to discuss agent design patterns! -
Token Speed Critical for Agentic AI Workflows
By
–
Yes, with agentic workflows, super fast token generation (like @groq
) becomes very important to overall system speed. If an LLM were generating tokens only for human consumption, then there's not much value to generating much faster than human reading speed. But with agentic