Conf42 Courses

Adding Generative AI to Real-Time Streaming Pipelines - Conf42 LLMs 2024

Explore integrating generative AI into real-time streaming pipelines, covering enterprise use cases, model selection, and implementation using tools like NiFi, Flink SQL, and cloud services.

• YouTube
• 26 minutes
• On-Demand
• Free Video

LLMs for Better Developer Learning of Your Product

Explore how LLMs revolutionize developer relations, enhance product learning, and create AI-powered documentation tools. Learn to build custom LLM apps for improved developer experiences.

• YouTube
• 21 minutes
• On-Demand
• Free Video

LLMs and AWS: Observability Maturity from Foundation to AIOps

Explore LLM observability maturity in AWS, from foundational concepts to advanced AIOps, covering metrics, performance, security, and best practices for effective implementation.

• YouTube
• 33 minutes
• On-Demand
• Free Video

Superposition in LLM Feature Representations

Explore mechanistic interpretability and superposition in LLM feature representations, focusing on neural network qualities, linearity, and sparsity to uncover hidden features and improve model understanding.

• YouTube
• 47 minutes
• On-Demand
• Free Video

Measuring Hallucinations in RAG - Retrieval Augmented Generation

Explore techniques to measure and mitigate hallucinations in Retrieval-Augmented Generation (RAG) systems, with practical examples and insights on improving LLM-based applications.

• YouTube
• 20 minutes
• On-Demand
• Free Video

Make LLM Apps Sane Again - Forgetting Incorrect Data in Real Time

Explore real-time data correction in LLM applications using vector indexing. Learn to build a chatbot that adapts to changing information, ensuring accuracy and reliability in AI-powered conversations.

• YouTube
• 21 minutes
• On-Demand
• Free Video

AI Chats: The Conundrums of Business Integration

Explore challenges and solutions for integrating AI chatbots in business, focusing on practical implementation and overcoming common obstacles.

• YouTube
• 36 minutes
• On-Demand
• Free Video

Getting AI to Do the Unexpected - Exploring LLM Vulnerabilities and Defenses

Explore LLM vulnerabilities, attacks, and defenses. Learn about prompt injections, output handling, and jailbreaking. Discover secure practices for AI implementation and see real-world examples.

• YouTube
• 32 minutes
• On-Demand
• Free Video

A Practical Guide to Securing Your AI Application

Explore practical strategies for securing AI applications, from responsible AI principles to vulnerability control and evaluation techniques. Learn to implement guardrails and observability in generative AI projects.

• YouTube
• 33 minutes
• On-Demand
• Free Video

Running an Open Source LLM - Deployment and Cost Considerations

Explore the process of running open-source LLMs, covering infrastructure, deployment, costs, and key learnings for effective implementation in real-world scenarios.

• YouTube
• 26 minutes
• On-Demand
• Free Video

The Power of GenAI: Generate Growth and Innovation with Data

Explore how GenAI and data drive innovation, growth, and personalized experiences. Learn about RAG, vector embeddings, and building data foundations for AI applications.

• YouTube
• 25 minutes
• On-Demand
• Free Video

How Well Do LLMs Detect Anomalies in Your Data? - Conf42 LLMs 2024

Explore LLMs' effectiveness in detecting data anomalies, understand data quality importance, and learn practical techniques for anomaly detection using OpenAI and BigQuery.

• YouTube
• 25 minutes
• On-Demand
• Free Video

Building an LLM Vulnerability Scanner to Secure AI Applications

Develop an LLM vulnerability scanner to audit and secure AI applications. Learn about LLM security risks and build a CLI tool for detecting vulnerabilities in AI systems.

• YouTube
• 32 minutes
• On-Demand
• Free Video

Operational Excellence for LLMs Using Amazon Bedrock - Conf42 LLMs 2024

Explore operational excellence for LLMs using Amazon Bedrock. Learn design principles, LLMOps, model lifecycle, customization, and architectural patterns for effective implementation and evaluation.

• YouTube
• 33 minutes
• On-Demand
• Free Video

Hono: Multi-Runtime Web Framework for the Edges

Explore Hono, a versatile web framework for edge computing. Learn about JavaScript runtimes, WinterCG standards, and Hono's key features like flexibility, speed, type safety, and middleware support.

• YouTube
• 23 minutes
• On-Demand
• Free Video