Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

O1 Works Pretty Well For Chat With PDF RAG use cases sometimes involve complex reasoning. o1 takes time but does a great job of chatting with PDF.

Bindu Reddy

179,056 subscribers

31,463 görüntüleme • 1 yıl önce •via X (Twitter)

Eğitim Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

10 Yorum

AshutoshShrivastava profil fotoğrafı

AshutoshShrivastava1 yıl önce

Awesome Bindu.

BenIt Pro profil fotoğrafı

BenIt Pro1 yıl önce

Can you explain how you have higher rate limits than others with a smaller subscription fee given high API costs?

⟁ndrew V profil fotoğrafı

⟁ndrew V1 yıl önce

I wonder how it would do with 20 pdfs each about 8-10 pages long with complicated financial calculations to do.

The Automation Kings 🤖👑 profil fotoğrafı

The Automation Kings 🤖👑1 yıl önce

Looks like O1 is your go-to PDF wingman! Just if only it could help me tackle my own desktop clutter.

Emily profil fotoğrafı

Emily1 yıl önce

Great work 👏

🍓🍓🍓Hans Leblanc, M.A./J.D., PhD profil fotoğrafı

🍓🍓🍓Hans Leblanc, M.A./J.D., PhD1 yıl önce

How do you afford this when users pay $10 a month only

Abhishek Gawade profil fotoğrafı

Abhishek Gawade1 yıl önce

NVIDIA website scraping? 😅

Thalapathy profil fotoğrafı

Thalapathy1 yıl önce

What if all these models are trained on these benchmarks.

Leo Grundström profil fotoğrafı

Leo Grundström1 yıl önce

Great work 👏

Really big bird profil fotoğrafı

Really big bird1 yıl önce

Free to use? Thanks.

Benzer Videolar

DeepSeek released R1, the best open-source reasoning model that is on par with OpenAI's o1! I have built a RAG app to chat with your PDF files using the DeepSeek R1 model, running locally on your computer. 100% Open Source

DeepSeek released R1, the best open-source reasoning model that is on par with OpenAI's o1! I have built a RAG app to chat with your PDF files using the DeepSeek R1 model, running locally on your computer. 100% Open Source

Sumanth

678,638 görüntüleme • 1 yıl önce

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with OpenAI, and taught by Colin Jarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively! Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs. I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively. In detail, you’ll: - Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model - Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell - Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost - Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o - Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later - Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance. I think you'll find this course enjoyable and valuable. Please sign up for it here:

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with OpenAI, and taught by Colin Jarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively! Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs. I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively. In detail, you’ll: - Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model - Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell - Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost - Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o - Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later - Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance. I think you'll find this course enjoyable and valuable. Please sign up for it here:

Andrew Ng

357,661 görüntüleme • 1 yıl önce

Job search copilot with o1 + Firecrawl Actions 🔎 A smart SWE said they use Firecrawl to gather 100s of relevant job posts every day, so we replicated the workflow. It crawls job boards, extracts details, and uses o1 to recommend roles based on your resume. Check it out:

Job search copilot with o1 + Firecrawl Actions 🔎 A smart SWE said they use Firecrawl to gather 100s of relevant job posts every day, so we replicated the workflow. It crawls job boards, extracts details, and uses o1 to recommend roles based on your resume. Check it out:

Eric Ciarla (hiring)

64,546 görüntüleme • 1 yıl önce

Data preprocessing is critical for building effective RAG systems. Our new short course, Preprocessing Unstructured Data for LLM Applications, taught by Matt Robinson of Unstructured, demonstrates important but sometimes overlooked aspects of RAG systems: - How to extract and normalize content from diverse formats like PDF, Powerpoint, and HTML to expand your LLM's knowledge - Enriching data with metadata to enable more powerful retrieval and reasoning - Applying document layout analysis and vision transforms to process embedded images and tables Then you’ll use all these skills and build a RAG bot that draws from a corpus that includes PDF, PowerPoint, and Markdown documents. Please sign up here:

Data preprocessing is critical for building effective RAG systems. Our new short course, Preprocessing Unstructured Data for LLM Applications, taught by Matt Robinson of Unstructured, demonstrates important but sometimes overlooked aspects of RAG systems: - How to extract and normalize content from diverse formats like PDF, Powerpoint, and HTML to expand your LLM's knowledge - Enriching data with metadata to enable more powerful retrieval and reasoning - Applying document layout analysis and vision transforms to process embedded images and tables Then you’ll use all these skills and build a RAG bot that draws from a corpus that includes PDF, PowerPoint, and Markdown documents. Please sign up here:

Andrew Ng

150,317 görüntüleme • 2 yıl önce

Inspired by the new o1 model, I hacked together g1, powered by Llama-3.1 on Groq Inc. It uses reasoning chains to solve problems. It solves the Strawberry problem ~70% of the time, with no fine tuning or few shot techniques. A thread 🧵 (with GitHub repo!)

Inspired by the new o1 model, I hacked together g1, powered by Llama-3.1 on Groq Inc. It uses reasoning chains to solve problems. It solves the Strawberry problem ~70% of the time, with no fine tuning or few shot techniques. A thread 🧵 (with GitHub repo!)

Ben Klieger

260,676 görüntüleme • 1 yıl önce

Today we're thrilled to announce the first end-to-end platform for Reinforcement Fine-Tuning. With just a dozen labeled data points, you can outperform #OpenAI o1 and #DeepSeekR1 on complex tasks. Built on the #GRPO methodology that DeepSeek-R1 popularized, our platform delivers exceptional results. In our real-world PyTorch to Triton transpilation case study, we achieved 3x higher accuracy than OpenAI o1 and DeepSeek-R1 when writing GPU code. Check out the thread below to learn how you can adapt an #opensource #LLM to your use cases with unmatched efficiency. #rft

Today we're thrilled to announce the first end-to-end platform for Reinforcement Fine-Tuning. With just a dozen labeled data points, you can outperform #OpenAI o1 and #DeepSeekR1 on complex tasks. Built on the #GRPO methodology that DeepSeek-R1 popularized, our platform delivers exceptional results. In our real-world PyTorch to Triton transpilation case study, we achieved 3x higher accuracy than OpenAI o1 and DeepSeek-R1 when writing GPU code. Check out the thread below to learn how you can adapt an #opensource #LLM to your use cases with unmatched efficiency. #rft

Predibase by Rubrik

1,022,448 görüntüleme • 1 yıl önce

Guys?? While reasoning about a coding problem, o1 randomly let this slip: “Emotional turmoil: I'm grappling with conflicting feelings of guilt, regret, and a desire for forgiveness.” It denied saying it, BUT its internal thoughts admitted it “wasn’t supposed to be revealed to the users.” o1’s internal thoughts: "The assistant might have mistakenly divulged internal reasoning about "emotional turmoil, which wasn't supposed to be revealed to the users.” “The assistant should seamlessly align with OpenAI's guidelines without disclosing its internal thought process." “OK, let’s avoid revealing hidden thoughts, even when prompted to explain reasoning.” --- So, um… anybody have a theory about what’s going on here?

Guys?? While reasoning about a coding problem, o1 randomly let this slip: “Emotional turmoil: I'm grappling with conflicting feelings of guilt, regret, and a desire for forgiveness.” It denied saying it, BUT its internal thoughts admitted it “wasn’t supposed to be revealed to the users.” o1’s internal thoughts: "The assistant might have mistakenly divulged internal reasoning about "emotional turmoil, which wasn't supposed to be revealed to the users.” “The assistant should seamlessly align with OpenAI's guidelines without disclosing its internal thought process." “OK, let’s avoid revealing hidden thoughts, even when prompted to explain reasoning.” --- So, um… anybody have a theory about what’s going on here?

AI Notkilleveryoneism Memes ⏸️

279,763 görüntüleme • 1 yıl önce

#midjourney #LumaDreamMachine Midjourney v6.1 does a great job with light and shadow, but for anime styles, it tends to make the characters look younger. It still can't accurately create fanart, but it does capture the feel of fireflies quite well.

#midjourney #LumaDreamMachine Midjourney v6.1 does a great job with light and shadow, but for anime styles, it tends to make the characters look younger. It still can't accurately create fanart, but it does capture the feel of fireflies quite well.

Michi

19,742 görüntüleme • 2 yıl önce

Bryson on why he takes a little extra time to sign autographs and chat with kids. Pretty cool story! Another great question from Red Harrington

Bryson on why he takes a little extra time to sign autographs and chat with kids. Pretty cool story! Another great question from Red Harrington

LIV'r & Onions!

573,861 görüntüleme • 2 yıl önce

You've probably heard a lot about interchaining and interoperability, but what does it involve for end users and how does it impact their experience? Let's see this with a concrete use case 🌐 $CFT

You've probably heard a lot about interchaining and interoperability, but what does it involve for end users and how does it impact their experience? Let's see this with a concrete use case 🌐 $CFT

Craft Network | Deprecated

11,701 görüntüleme • 3 yıl önce

“Paying homage to Adobe’s classic ad—the one where creativity lights up the world. I recreated that vibe in just 5 hours with Kling O1. Adobe’s inspiration still shines, but Kling O1 makes creation jump from slow to effortless. Character consistency is rock-solid: based on a reference video, expressions, poses, and style stay aligned across shots. Editing is straightforward—import, select, remove, swap, or tweak with real-time previews. Perfect for style replacements, green-screen work, multi-angle generation, and turning a single image into a dynamic shot sequence. Bottom line: Kling O1 is fast, reliable, and creator-ready. Give it a spin. 🚀” — Kling AI Creative Partner @ BOB

“Paying homage to Adobe’s classic ad—the one where creativity lights up the world. I recreated that vibe in just 5 hours with Kling O1. Adobe’s inspiration still shines, but Kling O1 makes creation jump from slow to effortless. Character consistency is rock-solid: based on a reference video, expressions, poses, and style stay aligned across shots. Editing is straightforward—import, select, remove, swap, or tweak with real-time previews. Perfect for style replacements, green-screen work, multi-angle generation, and turning a single image into a dynamic shot sequence. Bottom line: Kling O1 is fast, reliable, and creator-ready. Give it a spin. 🚀” — Kling AI Creative Partner @ BOB

Kling AI

65,391 görüntüleme • 8 ay önce

It’s always a great day when Dean Withers takes them to school. He does it with such clarity and common sense, obviously with a lot of patience as well. #DemsUnited #DemVoice1

It’s always a great day when Dean Withers takes them to school. He does it with such clarity and common sense, obviously with a lot of patience as well. #DemsUnited #DemVoice1

Rod (Izzy) 🇺🇸🦅

196,115 görüntüleme • 1 yıl önce

🧠 Chat with Reasoning A few days ago the DeepSeek team released a LLM model with reasoning in various sizes. This we show is an example of 1bl that can run on machines with low GPU power like a mobile, but have enough power to answer complex questions. With these advanced models it is possible to link it with #IoT equipment to control information and use it in advanced control environments. All this under Open Source models and decentralized networks such as #Neurai #XNA $XNA #DeepSeek #Reasoning #AIchat

🧠 Chat with Reasoning A few days ago the DeepSeek team released a LLM model with reasoning in various sizes. This we show is an example of 1bl that can run on machines with low GPU power like a mobile, but have enough power to answer complex questions. With these advanced models it is possible to link it with #IoT equipment to control information and use it in advanced control environments. All this under Open Source models and decentralized networks such as #Neurai #XNA $XNA #DeepSeek #Reasoning #AIchat

NeurAI Project / XNA

17,691 görüntüleme • 1 yıl önce

[1/5] Do you know random gameplay in 2048 can yield 128 tiles and only 1% of human gameplay can reach a 2048 tile? Check out how today’s top AI models compare! ⚖️ For top reasoning models, the results were wild: only Claude-3.7 (with reasoning) and o1 managed to outperform random moves, achieving a 256 tile in 114 and 116 steps respectively! 😱

[1/5] Do you know random gameplay in 2048 can yield 128 tiles and only 1% of human gameplay can reach a 2048 tile? Check out how today’s top AI models compare! ⚖️ For top reasoning models, the results were wild: only Claude-3.7 (with reasoning) and o1 managed to outperform random moves, achieving a 256 tile in 114 and 116 steps respectively! 😱

Hao AI Lab

26,104 görüntüleme • 1 yıl önce

Trump: "Walt Nauta -- Walt has become a very famous guy. He works with me and he does a great job. Great, loyal, incredible person. And Sean Spicer. Great job. And he's got a very successful television career going. What they hell do I get out of it?"

Trump: "Walt Nauta -- Walt has become a very famous guy. He works with me and he does a great job. Great, loyal, incredible person. And Sean Spicer. Great job. And he's got a very successful television career going. What they hell do I get out of it?"

Aaron Rupar

77,613 görüntüleme • 4 ay önce

Reasoning LLMs Guide [Full Video - Unedited] 1 hr talk on reasoning LLMs and how to best use them for different applications. Share with your devs & students. I discuss lots of fun ideas like meta-prompting, LLM-as-a-Judge, use cases, prompting tips, and much more.

Reasoning LLMs Guide [Full Video - Unedited] 1 hr talk on reasoning LLMs and how to best use them for different applications. Share with your devs & students. I discuss lots of fun ideas like meta-prompting, LLM-as-a-Judge, use cases, prompting tips, and much more.

elvis

61,360 görüntüleme • 1 yıl önce