![If AIs So Good, Why Cant It Make Its Own Data? [SEAL] @bycloudAI](https://i.ytimg.com/vi/uOO02o4J5KU/maxresdefault.jpg)
Uploaded July 2025 | Updated September 2026, 2 weeks ago
Get started now with privacy focused VPN by Proton! proton.me/pass/bycloudai
Can a neural network write its own data and skyrocket past GPT-4? In today's video, we dissect the brand-new “Self-Adapting Language Models” paper (SEAL), where an LLM fabricates synthetic data, tunes LoRA adapters, and after just two rounds, outperforms much larger models on SQuAD and ARC.
Self-Adapting Language Models
[Paper] arxiv.org/abs/2506.10943
My Newsletter
mail.bycloud.ai
my project: find, discover & explain AI research semantically
findmypapers.ai
My Patreon
patreon.com/c/bycloud
Try out my new fav place to learn how to code scrimba.com/?via=bycloudAI
This video is supported by the kind Patrons & YouTube Members:
🙏Nous Research, Chris LeDoux, Ben Shaener, DX Research Group, Poof N' Inu, Andrew Lescelius, 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
[Discord] discord.gg/NhJZGtH
[Twitter] twitter.com/bycloudai
[Patreon] patreon.com/bycloud
[Business Inquiries] bycloud@smoothmedia.co
[Profile & Banner Art] twitter.com/pygm7
[Video Editor] Abhay
[Ko-fi] ko-fi.com/bycloudai
Get started now with privacy focused VPN by Proton! proton.me/pass/bycloudai
Can a neural network write its own data and skyrocket past GPT-4? In today's video, we dissect the brand-new “Self-Adapting Language Models” paper (SEAL), where an LLM fabricates synthetic data, tunes LoRA adapters, and after just two rounds, outperforms much larger models on SQuAD and ARC.
Self-Adapting Language Models
[Paper] arxiv.org/abs/2506.10943
My Newsletter
mail.bycloud.ai
my project: find, discover & explain AI research semantically
findmypapers.ai
My Patreon
patreon.com/c/bycloud
Try out my new fav place to learn how to code scrimba.com/?via=bycloudAI
This video is supported by the kind Patrons & YouTube Members:
🙏Nous Research, Chris LeDoux, Ben Shaener, DX Research Group, Poof N' Inu, Andrew Lescelius, 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
[Discord] discord.gg/NhJZGtH
[Twitter] twitter.com/bycloudai
[Patreon] patreon.com/bycloud
[Business Inquiries] bycloud@smoothmedia.co
[Profile & Banner Art] twitter.com/pygm7
[Video Editor] Abhay
[Ko-fi] ko-fi.com/bycloudai
![If AIs So Good, Why Cant It Make Its Own Data? [SEAL]](https://i.ytimg.com/vi/uOO02o4J5KU/mqdefault.jpg "If AIs So Good, Why Cant It Make Its Own Data? [SEAL]
Get started now with privacy focused VPN by Proton! https://proton.me/pass/bycloudai
Can a neural network write its own data and skyrocket past GPT-4? In todays video, we dissect the brand-new “Self-Adapting Language Models” paper (SEAL), where an LLM fabricates synthetic data, tunes LoRA adapters, and after just two rounds, outperforms much larger models on SQuAD and ARC.
Self-Adapting Language Models
[Paper] https://arxiv.org/abs/2506.10943
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
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:
🙏Nous Research, Chris LeDoux, Ben Shaener, DX Research Group, Poof N Inu, Andrew Lescelius, 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
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Business Inquiries] bycloud@smoothmedia.co
[Profile & Banner Art] https://twitter.com/pygm7
[Video Editor] Abhay
[Ko-fi] https://ko-fi.com/bycloudai")
![New AI Meta: Train LLMs To Explore On Hard Tokens [RLVR + Entropy]](https://i.ytimg.com/vi/uOrJUksvIhs/mqdefault.jpg "New AI Meta: Train LLMs To Explore On Hard Tokens [RLVR + Entropy]
Get started with Strands Agents today:
https://aws.amazon.com/blogs/opensource/introducing-strands-agents-1-0-production-ready-multi-agent-orchestration-made-simple/?trk=3fa00bba-d2bc-45e2-a2b0-f96bc12fd521&sc_channel=psm
In this video, I will be sharing how researchers train LLMs to explore during RL to improve performance via entropy.
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
Beyond the 80/20 Rule
[Paper] https://arxiv.org/abs/2506.01939
Reasoning with Exploration
[Paper] https://arxiv.org/abs/2506.14758
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:
🙏Nous Research, Chris LeDoux, Ben Shaener, DX Research Group, Poof N Inu, Andrew Lescelius, 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
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Business Inquiries] bycloud@smoothmedia.co
[Profile & Banner Art] https://twitter.com/pygm7
[Video Editor] @Booga04
[Ko-fi] https://ko-fi.com/bycloudai")
![DeepSeeks Insane Architecture Breakthrough [Engram Explained]](https://i.ytimg.com/vi/xUlX6jvwVfM/mqdefault.jpg "DeepSeeks Insane Architecture Breakthrough [Engram Explained]
Stop scraping manually and check out SerpApi now!
https://serpapi.link/bycloud-march-2026
In this video, we will breakdown how DeepSeeks new engram works intuitively, with visualizations!
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
DeepSeek Engram
[Paper] https://arxiv.org/abs/2601.07372v1
mentioned papers
[DeepSeek-V3.2] https://arxiv.org/abs/2512.02556
[DeepSeek Sparse Attention] https://github.com/deepseek-ai/DeepSeek-V3.2-Exp/blob/main/DeepSeek_V3_2.pdf
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] bycloud@smoothmedia.co
[Music] @IraStoria
[Profile & Banner Art] https://twitter.com/pygm7
[Video Editor] Abhay
[Ko-fi] https://ko-fi.com/bycloudai")
![We had Image Gen copying LLM... and now the REVERSE?? [DiffusionLM]](https://i.ytimg.com/vi/yXHSPzHfe1s/mqdefault.jpg "We had Image Gen copying LLM... and now the REVERSE?? [DiffusionLM]
To try everything Brilliant has to offer—free—for a full 30 days, visit https://brilliant.org/bycloud/ . You’ll also get 20% off an annual premium subscription.
In 2023, image generation adopted LLMs transformer architecture to improve generation quality. Now, in 2024, the Diffusion Language Model, also known as DiffusionLM, is taking a step towards using diffusion for language modeling. Look how the turn tables...
my newsletter
https://mail.bycloud.ai
Check out my Patreon for the latest diffusionLM papers mapped out
https://www.patreon.com/bycloud
Structured Denoising Diffusion Models in Discrete State-Spaces
[Paper] https://arxiv.org/abs/2107.03006
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
[Paper] https://arxiv.org/abs/2310.16834
Scaling up Masked Diffusion Models on Text
[Paper] https://arxiv.org/abs/2410.18514
Discrete Diffusion for Complex Reasoning and Planning
[Paper] https://arxiv.org/abs/2410.14157
Simplified and Generalized Masked Diffusion for Discrete Data
[Paper] https://arxiv.org/abs/2406.04329
Speculative Diffusion Decoding
[Paper] https://arxiv.org/abs/2408.05636
Energy-Based Diffusion Language Models for Text Generation
[Paper] https://arxiv.org/abs/2410.21357
This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, Ben Shaener, Chris LeDoux, Miguilim, Deagan, FiFaŁ, Robert Zawiasa, Marcelo Ferreira, Owen Ingraham, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Penumbraa, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi, Hector, Drexon, Claxvii 177th, Inferencer, Michael Brenner, Akkusativ, Oleg Wock, FantomBloth, Thipok Tham, Clayton Ford, Theo, Handenon, Diego Silva, mayssam, Kadhai Pesalam, Tim Schulz, jiye, Anushka, Henrik Sundt, Julian Aßmann, Raffay Rana
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Profile & Banner Art] https://twitter.com/pygm7
[Video Editor] @Askejm
[Bitcoin (BTC)] 3JFMJQVGXNA2HJE5V9qCwLiqy6wHY9Vhdx
[Ethereum (ETH)] 0x3d784F55E0bE5f35c1566B2E014598C0f354f190
[Litecoin (LTC)] MGHnqALjyU2W6NuJSSW9fTWV4dcHfwHZd7
[Bitcoin Cash (BCH)] 1LkyGfzHxnSfqMF8tN7ZGDwUTyBB6vcii9
[Solana (SOL)] 6XyMCEdVhtxJQRjMKgUJaySL8cGoBPzzA2NPDMPfVkKN
[Ko-fi] https://ko-fi.com/bycloudai")
