Chunking

topic on 2 shows · 3 statements across 2 episodes

the Knowledge Project Latent Space

3 statements about Chunking, every show

LATENT SPACE Disclosure
Eugene Yan: Removing document chunking boosted pipeline downstream metrics by 50%
“I was asked to help with a pipeline, and I was able to improve downstream metrics significantly by 20 to 50% by removing chunking.”
Eugene Yan Nov 29, 2024 ▶ 16:15 [Paper Club] DocETL: Agentic Query Rewriting + Eval for Complex Document Processing w Shreya Shankar
Shreya Shankar: Chunking efficacy is task-specific, requiring automated pipeline optimization
“Sometimes it's beneficial to chunk and sometimes you should not chunk. And we have observed this in a number of workloads and the insight that we've gained is that we will never know what it's all task specific and data specific. And we are so further convince…”
Shreya Shankar Nov 29, 2024 ▶ 19:31 [Paper Club] DocETL: Agentic Query Rewriting + Eval for Complex Document Processing w Shreya Shankar
Oakley: Skill acquisition requires linking small cognitive chunks into larger patterns
“First, to be aware that there's a way of crystallizing what you're doing that creates a pattern that is a chunk. And you can make a bigger pattern, right? Just like a chain, and you can add more links to the chain.”
Barbara Oakley Apr 10, 2018 ▶ 56:08 #31 Barbara Oakley: Learning How to Learn

← every entity, every show

Made with StarZero

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.