AI21 Labs releases two AI Engineer Fair talks online
The chunking talk signals that naive fixed-size splitting of documents is losing ground to structure-aware approaches in production RAG systems. Engineers building retrieval pipelines can use it to re-evaluate their chunking strategies, and anyone running vLLM in production gets a concrete debugging walkthrough. Watching both takes well under an hour.
AI21 Labs published recordings of its two talks from the AI Engineer World's Fair.
The first talk, titled "Stop chunking like it's 2022", examines why traditional document chunking methods in RAG pipelines are outdated.
The second talk walks through debugging vLLM, framed as a detective story.Both videos are available to watch online.
Catch up with our two talks from @aiDotEngineer World's Fair, now available online👇
Stop chunking like it's 2022: https://t.co/OwZEsPbYKJ
A vLLM debugging detective story: https://t.co/sDphlsYztY
This report is categorized under AITOP's "How-to" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include AI21 Labs, RAG, vLLM, prompt engineering.
Source attribution: curated from AI21 Labs (@AI21Labs).
