Back to Agenda
Developer Day
Apr 17, 2025
3:50 pm
-
4:05 pm

[Panel] Choosing the Right Approach: When to Use Long Context Windows, Fine-Tuning, or Retrieval-Augmented Generation

Add to Calendar Apr 17, 2025 Apr 17, 2025 America/Los_Angeles [Panel] Choosing the Right Approach: When to Use Long Context Windows, Fine-Tuning, or Retrieval-Augmented Generation In this panel, industry experts discuss how developers can choose the right AI technique by comparing long context windows, fine tuning, and retrieval augmented generation based on their project needs. Speakers will cover real world factors such as cost, speed, and accuracy, while highlighting best practices for integrating each approach into existing workflows. Attendees will gain a practical understanding of when to rely on a larger context window, how to tailor models with fine tuning, and ways to incorporate external knowledge through retrieval. The goal is to provide actionable guidance for maximizing AI’s impact without compromising quality or performance. Main Stage | Gateway Pavilion - Pier 2 | 2 Marina Blvd, San Francisco, CA 94123

About this session

In this panel, industry experts discuss how developers can choose the right AI technique by comparing long context windows, fine tuning, and retrieval augmented generation based on their project needs. Speakers will cover real world factors such as cost, speed, and accuracy, while highlighting best practices for integrating each approach into existing workflows. Attendees will gain a practical understanding of when to rely on a larger context window, how to tailor models with fine tuning, and ways to incorporate external knowledge through retrieval. The goal is to provide actionable guidance for maximizing AI’s impact without compromising quality or performance.

Session Speaker

David Kanter

Founder, Head of MLPerf
MLCommons

Hina Dixit

Co-Founder & CEO
Decompute

Davit Buniatyan

Founder & CEO
Activeloop
Access Slides

More sessions

Developer Day
Apr 17, 2025
9:40 am

The Full Stack of Open Generative Ai

Join an AI expert from Meta for an in depth look at the latest advancements in the open generative AI stack. This session will cover from the metal to the agent how large scale AI systems are built, the tools used and how you can build your own with open source AI from Meta including PyTorch, Triton, Llama and more.

Joe Spisak
|
Meta
More Information
Developer Day
Apr 17, 2025
10:00 am

Ensuring Responsible AI with Advanced Model Evaluation

This session will cover Sama's comprehensive Model Evaluation services, emphasizing the importance of aligning AI systems with ethical guidelines and improving their performance. Attendees will learn how to systematically assess AI outputs, identify inaccuracies and vulnerabilities, and employ strategies for accelerated time-to-market with robust model validation. Leveraging Sama's expert-driven platform, participants will discover how to build reliable, high-performing generative AI models while adhering to industry standards.

Duncan Curtis
|
Sama
More Information
Developer Day
Apr 17, 2025
10:20 am

Building Agents to Automate Knowledge Work

A huge promise of LLM-powered agents is to not only provide simple Q&A search interfaces, but to automate 50%+ of operational work that a knowledge worker typically does. A lot of the day-to-day of a knowledge worker - whether an investment analyst, customer agent, or engineer - is ingesting a large volume of unstructured data and using that to synthesize new insights or take actions. This talk walks through the e2e architecture for building production knowledge agents that can actually do useful work over your data. This requires both a production-quality knowledge management layer as well as agent architectures that can reliably solve certain use cases.

Jerry Liu
|
LlamaIndex
More Information
Browse Agenda