Long-Context: RAG is Dead, Long Live RAG

Lightning Lessons

Practical skills & tools to accelerate your career

Featured

Design

Long-Context: RAG is Dead, Long Live RAG

Hosted by "Dr. Greg" Loughnane and Chris "The LLM Wizard 🪄" Alexiuk

Share this lesson

332 students

Share this lesson

332 students

Go deeper with a course

The AI Engineering Bootcamp

"Dr. Greg" Loughnane and Chris "The Wiz 🪄" Alexiuk

What you'll learn

Long-context LLMs vs. RAG

Do these two options accomplish the same goal? How do we make performance versus cost tradeoffs between them?

How do we even know if long-context LLMs are good?

Evaluation for long-context LLMs is an emerging discipline. Meet "Needle in a Haystack," "Ruler," and what's next!

How did Gradient increase Llama 3 8B from 8k context to 4M?

Technically, how was this done? What goes into this computationally and what are the implications for LLM development?

Why this topic matters

How long is long-context? What's the longest context that the industry finds useful? Why should I care about this topic when building LLM applications? In short, where should long-context LLMs fit into our mental model of the AI Engineering landscape? Join us live to find out and get your questions answered!

You'll learn from

"Dr. Greg" Loughnane

Co-Founder & CEO of AI Makerspace

Dr. Greg Loughnane is the Co-Founder & CEO of AI Makerspace, where he serves as an instructor for their AI Engineering Bootcamp. Since 2021 he has built and led industry-leading Machine Learning education programs. Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and an ML researcher. He loves trail running and is based in Dayton, Ohio.

Chris "The LLM Wizard 🪄" Alexiuk

Co-Founder & CTO of AI Makerspace

Chris “The Wiz” Alexiuk is the Co-Founder & CTO at AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. During the day, he is also a Developer Advocate at NVIDIA. Previously, he was a Founding Machine Learning Engineer, Data Scientist, and ML curriculum developer and instructor. He’s a YouTube content creator YouTube who’s motto is “Build, build, build!” He loves Dungeons & Dragons and is based in Toronto, Canada.

Previously at