Загрузка видео...

Не удалось загрузить видео

На главную

*Finally* read through Sam Rose's blog on LLM quantization. It's incredible. For many (even in tech) the understanding of how LLMs work stops at the surface level. Sam is helping us all go deeper, digging into the interesting facets of how AI models truly work. Read it!

BenjDicken's profile picture

Ben Dicken

40,843 subscribers

272,448 просмотров • 3 месяцев назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

New course! Generative AI with Large Language Models, created with Amazon Web Services and hosted on Coursera. This course goes deep into the technical foundations of LLMs and how to use them. You can sign up here: You’ll work through the full life-cycle of a generative AI project, and learn specific techniques like RLHF; zero-shot, one-shot, and few-shot learning with LLMs; advanced prompting frameworks like ReAct; even fine-tuning LLMs, and gain hands-on practice with all of these techniques. Instructors Antje Barth Chris Fregly Shelbee Eigenbrode and Mike G Chambers all do incredible Generative AI work at AWS, and have supported many companies to build creative LLM applications. They bring tremendous practical LLM expertise to this course. I'm confident you’ll finish this course with a deeper understanding of how LLMs work, and how to use them. I hope you enjoy the course!
1:57

New course! Generative AI with Large Language Models, created with Amazon Web Services and hosted on Coursera. This course goes deep into the technical foundations of LLMs and how to use them. You can sign up here: You’ll work through the full life-cycle of a generative AI project, and learn specific techniques like RLHF; zero-shot, one-shot, and few-shot learning with LLMs; advanced prompting frameworks like ReAct; even fine-tuning LLMs, and gain hands-on practice with all of these techniques. Instructors Antje Barth Chris Fregly Shelbee Eigenbrode and Mike G Chambers all do incredible Generative AI work at AWS, and have supported many companies to build creative LLM applications. They bring tremendous practical LLM expertise to this course. I'm confident you’ll finish this course with a deeper understanding of how LLMs work, and how to use them. I hope you enjoy the course!

Andrew Ng

467,882 просмотров • 3 лет назад

The lack of understanding of how current AI/ large language models work makes us susceptible to thinking that AI is more powerful and all-knowing than it actually is. That’s what concerns me the most.
2:09

The lack of understanding of how current AI/ large language models work makes us susceptible to thinking that AI is more powerful and all-knowing than it actually is. That’s what concerns me the most.

Sinead Bovell

143,642 просмотров • 3 лет назад

The age of AI agents is here. Models can read, see, talk, and now, even use a computer— all by themselves. One of the first out of the gates is Anthropic’s Claude Computer Use. YC's Garry Tan dives into how it works, what it can do, and how it may change AI forever.
7:53

The age of AI agents is here. Models can read, see, talk, and now, even use a computer— all by themselves. One of the first out of the gates is Anthropic’s Claude Computer Use. YC's Garry Tan dives into how it works, what it can do, and how it may change AI forever.

Y Combinator

265,897 просмотров • 1 год назад

How EMBARASSING for UCLA. Students can't even read at 6th grade level. This kid got into college because of the color of his skin.
0:40

How EMBARASSING for UCLA. Students can't even read at 6th grade level. This kid got into college because of the color of his skin.

Mila Joy

104,419 просмотров • 1 день назад

The Trump administration is coming for your data. All of it. Read more: ✍️ Sam Biddle 📹 jordan
1:13

The Trump administration is coming for your data. All of it. Read more: ✍️ Sam Biddle 📹 jordan

The Intercept

11,105 просмотров • 1 год назад

SAM 3 tackles a challenging problem in vision: unifying a model architecture for detection and tracking. Christoph, a researcher on SAM 3, shares how the team made it possible. 🔗 Read the SAM 3 research paper:
2:00

SAM 3 tackles a challenging problem in vision: unifying a model architecture for detection and tracking. Christoph, a researcher on SAM 3, shares how the team made it possible. 🔗 Read the SAM 3 research paper:

AI at Meta

13,803 просмотров • 7 месяцев назад

Isn't it interesting how many of the biggest critics of Trump's tariffs are on the CCP's payroll? Great work, Natalie Winters. 👊
2:11

Isn't it interesting how many of the biggest critics of Trump's tariffs are on the CCP's payroll? Great work, Natalie Winters. 👊

Rep. Eli Crane

201,502 просмотров • 1 год назад

Collecting a high quality dataset with 4M unique phrases and 52M corresponding object masks helped SAM 3 achieve 2x the performance of baseline models. Kate, a researcher on SAM 3, explains how the data engine made this leap possible. 🔗 Read the SAM 3 research paper:
2:05

Collecting a high quality dataset with 4M unique phrases and 52M corresponding object masks helped SAM 3 achieve 2x the performance of baseline models. Kate, a researcher on SAM 3, explains how the data engine made this leap possible. 🔗 Read the SAM 3 research paper:

AI at Meta

38,684 просмотров • 7 месяцев назад

The Sam Altman Interview You know him as the CEO of OpenAI — but he's also an avid writer. We spoke not once but twice about how Sam captures ideas, clarifies his thinking, edits his writing, decides what to work on, and uses ChatGPT. Timestamps: 1:47 Will LLMs change how we write? 8:39 How does Sam use ChatGPT? 11:26 How Sam became less anxious 17:24 Sam once dreamed of being a novelist 18:37 Lessons from Peter Thiel 21:35 Lessons from Paul Graham 26:02 The book Sam Altman wants to write 28:37 Advice for startup founders 30:20 How Y Combinator shapes OpenAI 35:55 How Sam chose to work on AGI 37:35 Writing strategy memos at OpenAI 41:34 Why isn’t ChatGPT a better storyteller? 44:20 Sam's obsessive note-taking method 47:12 Will AI put writers out of work?
48:38

The Sam Altman Interview You know him as the CEO of OpenAI — but he's also an avid writer. We spoke not once but twice about how Sam captures ideas, clarifies his thinking, edits his writing, decides what to work on, and uses ChatGPT. Timestamps: 1:47 Will LLMs change how we write? 8:39 How does Sam use ChatGPT? 11:26 How Sam became less anxious 17:24 Sam once dreamed of being a novelist 18:37 Lessons from Peter Thiel 21:35 Lessons from Paul Graham 26:02 The book Sam Altman wants to write 28:37 Advice for startup founders 30:20 How Y Combinator shapes OpenAI 35:55 How Sam chose to work on AGI 37:35 Writing strategy memos at OpenAI 41:34 Why isn’t ChatGPT a better storyteller? 44:20 Sam's obsessive note-taking method 47:12 Will AI put writers out of work?

David Perell

239,660 просмотров • 1 год назад

🚨 We’re hiring in NYC!!! 🚨 We’re looking for curious minds with a dash of explorer and a lot of grit. If you want to work on truly frontier AI (not just an LLM wrapper) and deploy it in some of the most interesting places in the world – join us in the Arena! Apply for open roles here:
0:30

🚨 We’re hiring in NYC!!! 🚨 We’re looking for curious minds with a dash of explorer and a lot of grit. If you want to work on truly frontier AI (not just an LLM wrapper) and deploy it in some of the most interesting places in the world – join us in the Arena! Apply for open roles here:

Pratap Ranade

17,520 просмотров • 2 лет назад

This is the best Visual Explanation of how LLMs actually work
1:00

This is the best Visual Explanation of how LLMs actually work

sachin.

345,688 просмотров • 4 месяцев назад

#Exclusive clip of Jennie describing how she met Sam Levinson, read the script for The Idol and enthusiastically agreed to join that nasty show. Sam repeatedly exposed for exploiting young women on set, and for building an empire on the pain of others.
0:32

#Exclusive clip of Jennie describing how she met Sam Levinson, read the script for The Idol and enthusiastically agreed to join that nasty show. Sam repeatedly exposed for exploiting young women on set, and for building an empire on the pain of others.

-

21,184 просмотров • 5 месяцев назад

It's amazing to see how many leftists - and even folks on the right - who have absolutely zero understanding of what modern manufacturing looks like. Yes, it's work boots and dirty hands. It's also machine learning, AI algorithms, statistics, and high level thinking. We are the Military Industrial Complex, and we are made in America.
0:51

It's amazing to see how many leftists - and even folks on the right - who have absolutely zero understanding of what modern manufacturing looks like. Yes, it's work boots and dirty hands. It's also machine learning, AI algorithms, statistics, and high level thinking. We are the Military Industrial Complex, and we are made in America.

Feni𝕏 Ammunition

98,332 просмотров • 1 год назад

"How many times does [Sam Darnold] have to win a game for us to give him the benefit of the doubt?" Peter Schrager and Stephen A Smith disagree on how much they believe in Sam Darnold 🍿
4:21

"How many times does [Sam Darnold] have to win a game for us to give him the benefit of the doubt?" Peter Schrager and Stephen A Smith disagree on how much they believe in Sam Darnold 🍿

First Take

75,858 просмотров • 8 месяцев назад

Announcing How Transformer LLMs Work, created with Jay Alammar and Maarten Grootendorst, co-authors of the beautifully illustrated book, “Hands-On Large Language Models.” This course offers a deep dive into the inner workings of the transformer architecture that powers large language models (LLMs). The transformer architecture revolutionized generative AI; in fact, the "GPT" in ChatGPT stands for "Generative Pre-Trained Transformer." Originally introduced in the Google Brain team's groundbreaking 2017 paper "Attention Is All You Need," by Vaswani and others, transformers were a highly scalable model for machine translation tasks. Variants of this architecture now power today’s LLMs such as those from OpenAI, Google, Meta, Cohere, Anthropic and DeepSeek. In this course, you’ll learn in detail how LLMs process text. You'll also work through code examples that illustrate that transformer's individual components. In details, you’ll learn: - How the representation of language has evolved, from Bag-of-Words to Word2Vec embeddings to the transformer architecture that captures a word's meanings taking into account the context of other words in the input. - How inputs are broken down into tokens before they are sent to the language model. - The details of a transformer's main stages: Tokenization and embedding, the stack of transformer blocks, and the language model head. - The inner workings of the transformer block, including attention, which calculates relevance scores, and the feedforward layer, which incorporates stored information learned in training. - How cached calculations make transformers faster. - Some of the most recent ideas in the latest models such as Mixture-of-Experts (MoE) which uses multiple sub-models and a router on each layer to improve the quality of LLMs. By the end of this course, you’ll have a deep understanding of how LLMs actually process text and be able to read through papers describing the latest models and understand the details. Gaining this intuition will improve your approach to building LLM applications. Please sign up here:
3:36

Announcing How Transformer LLMs Work, created with Jay Alammar and Maarten Grootendorst, co-authors of the beautifully illustrated book, “Hands-On Large Language Models.” This course offers a deep dive into the inner workings of the transformer architecture that powers large language models (LLMs). The transformer architecture revolutionized generative AI; in fact, the "GPT" in ChatGPT stands for "Generative Pre-Trained Transformer." Originally introduced in the Google Brain team's groundbreaking 2017 paper "Attention Is All You Need," by Vaswani and others, transformers were a highly scalable model for machine translation tasks. Variants of this architecture now power today’s LLMs such as those from OpenAI, Google, Meta, Cohere, Anthropic and DeepSeek. In this course, you’ll learn in detail how LLMs process text. You'll also work through code examples that illustrate that transformer's individual components. In details, you’ll learn: - How the representation of language has evolved, from Bag-of-Words to Word2Vec embeddings to the transformer architecture that captures a word's meanings taking into account the context of other words in the input. - How inputs are broken down into tokens before they are sent to the language model. - The details of a transformer's main stages: Tokenization and embedding, the stack of transformer blocks, and the language model head. - The inner workings of the transformer block, including attention, which calculates relevance scores, and the feedforward layer, which incorporates stored information learned in training. - How cached calculations make transformers faster. - Some of the most recent ideas in the latest models such as Mixture-of-Experts (MoE) which uses multiple sub-models and a router on each layer to improve the quality of LLMs. By the end of this course, you’ll have a deep understanding of how LLMs actually process text and be able to read through papers describing the latest models and understand the details. Gaining this intuition will improve your approach to building LLM applications. Please sign up here:

Andrew Ng

253,812 просмотров • 1 год назад

The worst thing is it doesn’t matter how corrupt this is, how illegal it is or how many people protest – even if it’s 99.6% of Australia – Finklestein is still going to get his $200,000 for doing SFA. It’s the cabal at work, right in front of us and we can’t do anything about it.
1:18

The worst thing is it doesn’t matter how corrupt this is, how illegal it is or how many people protest – even if it’s 99.6% of Australia – Finklestein is still going to get his $200,000 for doing SFA. It’s the cabal at work, right in front of us and we can’t do anything about it.

Eddy Jokovich

30,926 просмотров • 1 месяц назад

📣 A New 1517 Academy Course: Reading and Interpreting the Bible How should we read the Bible? In our new free course, Reading & Interpreting the Bible, Chad Bird walks through the grand story of Scripture from Genesis to Revelation and equips you with tools to read it with clarity and confidence. Learn how context and genre shape meaning, how the many voices of Scripture proclaim one unified story, and how all of it leads us to Christ. Enroll for free at the link in bio.
1:03

📣 A New 1517 Academy Course: Reading and Interpreting the Bible How should we read the Bible? In our new free course, Reading & Interpreting the Bible, Chad Bird walks through the grand story of Scripture from Genesis to Revelation and equips you with tools to read it with clarity and confidence. Learn how context and genre shape meaning, how the many voices of Scripture proclaim one unified story, and how all of it leads us to Christ. Enroll for free at the link in bio.

1517

10,042 просмотров • 4 месяцев назад

After two years of work, The Santiago Boys is finally live - you can listen to all the episodes on the main podcasting platforms. For an even deeper experience, do it on its website:
1:12

After two years of work, The Santiago Boys is finally live - you can listen to all the episodes on the main podcasting platforms. For an even deeper experience, do it on its website:

Evgeny Morozov

293,652 просмотров • 3 лет назад

What happens when a community-owned AI reaches 1+ million users? For the first time in history, AI doesn’t just get smarter. The people helping build it get stronger too. Not just investors. Not just board members. Not just billionaires. Ordinary people helping train the model share in the value it creates. That’s how the future of AI should work. That’s when things get truly interesting.
1:25

What happens when a community-owned AI reaches 1+ million users? For the first time in history, AI doesn’t just get smarter. The people helping build it get stronger too. Not just investors. Not just board members. Not just billionaires. Ordinary people helping train the model share in the value it creates. That’s how the future of AI should work. That’s when things get truly interesting.

Action Model

20,925 просмотров • 25 дней назад