Free Lesson
Long-Context: RAG is Dead, Long Live RAG
30 min
Jul 2, 2024 10:00 AM
Virtual (Zoom)
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
Chris "The LLM Wizard 🪄" Alexiuk
Co-Founder & CTO of AI Makerspace
Previously at
