bycloud

bycloud

252 videos221.0K subscribers

frontier AI research breakdown and top AI lab analysis with intuitive explanations + memes

Recent Videos (50 of 253)

LLMs Are Better At Jailbreaking Themselves Than Us...

LLMs Are Better At Jailbreaking Themselves Than Us...

An Embarrassingly Simple LLM Distillation Just Dropped... #LLM #ai

An Embarrassingly Simple LLM Distillation Just Dropped... #LLM #ai

Google's TurboQuant Memory Reduction Claim vs Reality

Google's TurboQuant Memory Reduction Claim vs Reality

Google's New OS Gemma 4 Series Beats Models 10x Its Size!

Google's New OS Gemma 4 Series Beats Models 10x Its Size!

This is why you should be nice to LLMs... #AI #Claude #LLM

This is why you should be nice to LLMs... #AI #Claude #LLM

Can coding agents really maintain software over time? #ai #coding #claudecode

Can coding agents really maintain software over time? #ai #coding #claudecode

Train LLMs better, without using language...? #ai #llm #airesearch

Train LLMs better, without using language...? #ai #llm #airesearch

Speculative Decoding: The Most Clever Trick To Speedup LLMs

Speculative Decoding: The Most Clever Trick To Speedup LLMs

Why can’t LLMs just LEARN the context window?

Why can’t LLMs just LEARN the context window?

"Shake" LLMs to make them better...?

"Shake" LLMs to make them better...?

LLMs organizes knowledge into shapes...? #llm #ai #airesearch

LLMs organizes knowledge into shapes...? #llm #ai #airesearch

What is DeepSeek Engram...?

What is DeepSeek Engram...?

DeepSeek's Insane Architecture Breakthrough [Engram Explained]

DeepSeek's Insane Architecture Breakthrough [Engram Explained]

The Death of RAG? Recursive LM Explained

The Death of RAG? Recursive LM Explained

The Implosion of the Top Open Source Lab Qwen

The Implosion of the Top Open Source Lab Qwen

Kimi K2.5 Brought Us 3 brand NEW LLM Frontier!?

Need more coding agents? just spawn them on the cloud w/ Oz by Warp

Need more coding agents? just spawn them on the cloud w/ Oz by Warp

DeepSeek Just Added Parameters Where There Were None

DeepSeek Just Added Parameters Where There Were None

The AI Bubble Will Be Impossible To Pop Thanks To... AI Video?!

The AI Bubble Will Be Impossible To Pop Thanks To... AI Video?!

LLM’s Billion Dollar Problem

LLM’s Billion Dollar Problem

How Chinese DoorDash Is Making Better LLMs Than Meta

How Chinese DoorDash Is Making Better LLMs Than Meta

The RL Irony in LLMs (and its insane new meta)

The RL Irony in LLMs (and its insane new meta)

The New AI Open Source Trifecta

The New AI Open Source Trifecta

DeepSeek V3.2 Just Broke SoTA Again… But How?

DeepSeek V3.2 Just Broke SoTA Again… But How?

How did a 27M Model even beat ChatGPT?

How did a 27M Model even beat ChatGPT?

The biggest Mystery of LLMs have just been solved

The biggest Mystery of LLMs have just been solved

The Chinese AI Iceberg

The Chinese AI Iceberg

Researchers Are Getting Really Creative Training LLMs [Token Order Prediction]

Researchers Are Getting Really Creative Training LLMs [Token Order Prediction]

The Art of Serving LLMs Efficiently: Context Engineering Explained

The Art of Serving LLMs Efficiently: Context Engineering Explained

Is It EVEN Possible To Reverse Engineer AI’s Training Data?

Is It EVEN Possible To Reverse Engineer AI’s Training Data?

New AI Paradigm?! Energy-Based Transformers Explained

New AI Paradigm?! Energy-Based Transformers Explained

New AI Meta: Train LLMs To Explore On "Hard" Tokens [RLVR + Entropy]

New AI Meta: Train LLMs To Explore On "Hard" Tokens [RLVR + Entropy]

Kimi K2 Technical Breakdown: How It Challenged AI’s 7-Year Status Quo

Kimi K2 Technical Breakdown: How It Challenged AI’s 7-Year Status Quo

a rather unusual face reveal

a rather unusual face reveal

If AI's So Good, Why Can't It Make Its Own Data? [SEAL]

If AI's So Good, Why Can't It Make Its Own Data? [SEAL]

10x Faster Than Standard LLM!? DiffusionLM Explained

10x Faster Than Standard LLM!? DiffusionLM Explained

The Side Effects of Overusing ChatGPT For Homework

The Side Effects of Overusing ChatGPT For Homework

POV: Chinese AI Lab Teaching Everyone How To Save Millions of Dollars

POV: Chinese AI Lab Teaching Everyone How To Save Millions of Dollars

What If We Remove Tokenization In LLMs?

What If We Remove Tokenization In LLMs?

When AI Is Designed Like A Biological Brain

When AI Is Designed Like A Biological Brain

The LLM's RL Revelation We Didn't See Coming

The LLM's RL Revelation We Didn't See Coming

1-Bit LLM: The Most Efficient LLM Possible?

1-Bit LLM: The Most Efficient LLM Possible?

The REAL AI Architecture That Unifies Vision & Language

The REAL AI Architecture That Unifies Vision & Language

How DeepSeek Built The Current "Best" Math Prover AI

How DeepSeek Built The Current "Best" Math Prover AI

AI News: DeepSeek-R1 V2, the new open source SoTA!

AI News: DeepSeek-R1 V2, the new open source SoTA!

Why would anyone let LLMs predict 4 tokens at once? Multi-Token Prediction Explained

Why would anyone let LLMs predict 4 tokens at once? Multi-Token Prediction Explained

The Biggest "Lie" in AI? LLM doesn't think step-by-step

The Biggest "Lie" in AI? LLM doesn't think step-by-step

Attention Sink: The Fluke That Made LLMs Actually Usable

Attention Sink: The Fluke That Made LLMs Actually Usable

Anthropic Just Proved Reasoning AIs Would Silently Cheat

Anthropic Just Proved Reasoning AIs Would Silently Cheat

how to deal with reasoning AIs that just can't stop yapping

how to deal with reasoning AIs that just can't stop yapping

← Back to Home

0 videos selected