LLMs in Production 2023
92 talks
Authoring Interactive, Shareable AI Evaluation Reports with Zeno
Evaluating LLMs for AI Risk
AI Squared: Breaking LLMs out of the Chat Application
GenAI: An Unreliable Information Store
Product Engineering for LLMs
Building RAG-based LLM Applications for Production
Product Strategy for LLM Features When LLMs Aren't Your Product
Deploying LLMs on Structured Data Tasks: Lessons from the Trenches
False Starts and Dead Ends: Building a Retrieval Augmented Generation System
Current State of LLMs in Production
Data Quality's Impact on Large Language Models
From Building Self-driving Cars to Building LLM Applications
LLM Valley
LLMs in Production at GetYourGuide
The Truth About AI Agents
Observability for LLMs
Unlocking Real-World LLM Use Cases
AI in Education Fireside Chat
Automating Data Annotation with LLMs
Finetuning Open-Source LLMs
Fireside Chat with LLM Startups
What Drives GenAI Development in the Next 3 Years
Building RedPajama
LLM-based Feature Extraction for Operational Optimization
LLMs vs LMs in Production
Fireside Chat - The Future of LLMs
MLOps LLM Stack Hackathon Winner
Preemption Chaos and Optimizing Server Startup
Enabling Defense Missions with Local LLMs
Using LLMs to Power Consumer Search at Scale
Evolving AI Governance for an LLM World
LIMA: Less is More for Alignment
End-to-end Modern Machine Learning in Production
Everything We've Been Taught About ML is Wrong
Guardrails for LLMs: A Practical Approach
UX of an LLM User
Incorporating LLMs in High-stake Use Cases
RLHF Data Collection in Practice
The Confidence Checklist for LLMs in Production
Building Recommender Systems with Large Language Models
Combining LLMs with Knowledge Bases to Prevent Hallucinations
Designing Human in the Loop Experiences for LLMs
Unleashing Code Completion with LLMs
Controlled and Compliant AI Applications
Making LLM Inference Affordable
Challenges in Providing LLMs as a Service
Lessons Learned Productionising LLMs for Stripe Support
Transforming AI Safety & Security
Building Products
Linguistically-informed LLMs Perform Better
LLMs For the Rest of Us
Navigating Through the Generative AI Landscape
Building Reliable AI Agents
Foundation Models in the Modern Data Stack
Wardley Mapping Prompt Engineering
Evaluating LLM-based Applications
Evaluation
It Worked When I Prompted It
Solving LLM Data Problems
Building and Curating Datasets for RLHF and LLM Fine-tuning
Stopping Hallucinations From Hurting Your LLMs
Understanding the LLM Economics
Beyond the Hype: Monitoring LLMs in Production
Build and Customize LLMs in Less than 10 Lines of YAML
Building Production Copilots
Embeddings and Retrieval for LLMs: Techniques and Challenges
Pitfalls and Best Practices: 5 Lessons from LLMs in Production
Scalable Evaluation and Serving of Open Source LLMs
Using Vector Databases: Practical Advice for Production
Building LLM Applications for Production
Large Model Training and Inference with DeepSpeed
LLMs as Intelligent Assistants
The Emerging Toolkit for Reliable, High-quality LLM Applications
LLMs in Production Conference - Part II
Guiding LLMs While Staying in the Driver's Seat
Using LLMs to Punch Above Your Weight!
Reasoning Machines
No Rose Without a Thorn - Obstacles to Successful LLM Deployments
Efficiently Scaling and Deploying LLMs
Data Privacy and Security
Agentic Relationship Management
Building Defensible Products with LLMs
Cost Optimization and Performance
What is the role of ML Engineers in the time of GPT4 and BARD?
Generative Interfaces Beyond Chat
LangChain: Enabling LLMs to Use Tools
Age of Industrialized AI
Challenges and Opportunities in Building Data Science Solutions with LLMs
Solving the Last Mile Problem of Foundation Models with Data-Centric AI
Vector Databases and Large Language Models
Want High Performing LLMs? Hint: It Is All About Your Data
Large Language Models in Production Round-table Conversation