48sec snip

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis cover image

Long-Term Memory for LLMs, with HippoRAG author Bernal Jiménez Gutierrez

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

NOTE

Cost-effective Model Selection Insight

Choosing a model with a size of 3.5 is much more cost-effective compared to other models like Plot, which is twice as expensive in inputs and ten times as expensive in outputs. Offline indexing is also costly, requiring the production of a significant number of open IE triples. Experimenting with models like Claude or GPT-40 would incur around $500 for a small subset of the benchmarks used in the study, which included a thousand questions and approximately 10,000 documents per benchmark.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode