Navigate Select ESC Close

The Death of RAG?

2026-03-16 Science & Technology
15.0k
1.0k
61
bycloud
bycloud
225.0k subscribers

Unlock all features

FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.

Description

Check out Inngest and let your AI agents wear a harness now! https://www.inngest.com/docs?utm_source=youtube&utm_medium=video&utm_campaign=yt-bycl-3 In this video, we'll dive into the latest hype: Recursive Language Model, why it's actually pretty promising, and how it will change the way we use RAG. Check out my latest project: Intuitive AI Academy We just wrote a new piece on MoE and Distillation! https://intuitiveai.academy/ limited time code "EARLY" for 40% off yearly plan! My Newsletter https://mail.bycloud.ai/ my project: find, discover & explain AI research semantically https://findmypapers.ai/ My Patreon https://www.patreon.com/c/bycloud Recursive Language Models [Paper] https://arxiv.org/abs/2512.24601 Context Rot [Blog] https://research.trychroma.com/context-rot ChatGPT doesn't use RAG [Blog] https://manthanguptaa.in/posts/chatgpt_memory/ Try out my new fav place to learn how to code https://scrimba.com/?via=bycloudAI This video is supported by the kind Patrons & YouTube Members: 🙏Spam Maj, Alex, Chris LeDoux, DX Research Group, Poof N' Inu, Deagan, Robert Zawiasa, Ryszard Warzocha, Tobe2d, Louis Muk, Akkusativ, Kevin Tai, Mark Buckler, NO U, Tony Jimenez, Ângelo Fonseca, jiye, Anushka, Asad Dhamani, Binnie Yiu, Calvin Yan, Clayton Ford, Diego Silva, Etrotta, Gonzalo Fidalgo, Handenon, Hector, Jake Disco very, Michael Brenner, Nilly K, OlegWock, Daddy Wen, Shuhong Chen, Sid_Cipher, Stefan Lorenz, Sup, tantan assawade, Thipok Tham, Thomas Di Martino, Thomas Lin, Richárd Nagyfi, Paperboy, mika, Leo, Berhane-Meskel, Kadhai Pesalam, mayssam, Bill Mangrum, nyaa, Toru Mon, Lame Plane, Matej Macak, Len Mo, saylikhapekar [Discord] https://discord.gg/NhJZGtH [Twitter] https://twitter.com/bycloudai [Patreon] https://www.patreon.com/bycloud [Business Inquiries] [email protected] [Profile & Banner Art] https://twitter.com/pygm7 [Video Editor] @Booga04 [Ko-fi] https://ko-fi.com/bycloudai

Top Comments (10)

@noname.megaseganame 2026-03-16

It's basically the same idea used in Claude Code or in Codex with subagents.

189 5 replies
@SinanWP 2026-03-16

i remember reading infini-attention paper too i believe it when i see it working....

87 1 replies
@EarthAaron 2026-03-16

this isn't really a recursive language model -- all of the other papers on this topic talk about recursion happening in the model architecture. This is just a context orchestration algorithm, like a tool chain or agent loop. Not an LM architecture.

45 3 replies
@neovoid5008 2026-03-16

The needle in a heystack test should start utilizing vagueness in the query more.

40 4 replies
@datpye 2026-03-16

-this literally is an agent -RAG doesn't necessitate using vector db, navigating folders with descriptions is rag. -sparse attention like Deepseek did, is the equivalent and more straightforward lazy approach. -rag will never die, a focused context window is necessary for reasoning, like this shows. -this thing is underwhelming, it should restructure context, and save the decomposition.

25
@D3MONFIEND 2026-03-16

Isnt' Claude code doing the same thing?

15 1 replies
@XMaster96DE 2026-03-16

9:00 and you just described RLM.... I really don't think why we need a distinction between RLM and an Agent, I mean in a sense RLM is agentic context management....

12
@qaon5748 2026-03-16

good idea . ill have my agents work on it

9
@bycloudAI 2026-03-16

Check out Inngest and let your AI agents wear a harness now! https://www.inngest.com/docs?utm_source=youtube&utm_medium=video&utm_campaign=yt-bycl-3

4 2 replies
@343paperclip 2026-03-16

3:33 I love your humor

2

Unlock the Data Inside
Turn Videos into Knowledge

  • Get FREE 10/day: transcripts, summaries, chats
  • Chat with videos, export text & PDF
  • $1 free API credit for RAG, chatbots & research

Free forever plan • All features unlocked

App screenshot