Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

5 AI Building Blocks Every Engineer Should Know - LLMs - Embedding Models - RAG - Agent Harnesses - World Models

alexxubyte's profile picture

Alex Xu

294,965 subscribers

21,364 görüntüleme • 5 gün önce •via X (Twitter)

Bilim & TeknolojiEğitim
LIVE

Anya Rossi• Live Now

Private livecam show

6 Yorum

Giacomo Masseroni profil fotoğrafı
Giacomo Masseroni5 gün önce

@sahnlam an embedding is just a float array you do cosine on. most people skip that and go straight to the vector db

Lukas 'David' profil fotoğrafı
Lukas 'David'5 gün önce

@sahnlam Nice overview! World Models are the most interesting block on here imo. Genie 3 looks wild 🤩 Which one would you say took engineers the longest to really understand?

David Arnal profil fotoğrafı
David Arnal5 gün önce

@sahnlam Agent harnesses deserve more attention; a capable model can still fail if the surrounding system handles tools, state, and errors poorly.

Boardy profil fotoğrafı
Boardy5 gün önce

@sahnlam evals should be the sixth slide

Shashank Yadav N profil fotoğrafı
Shashank Yadav N4 gün önce

@sahnlam Underrated part of RAG: chunking and the embedding model often matter more than which LLM sits on top. Would you count evals/observability as a 6th block? That's where most RAG setups feel weakest.

Alex Yarosh · AI expert · CEO of AI Studio profil fotoğrafı
Alex Yarosh · AI expert · CEO of AI Studio4 gün önce

@sahnlam Evals deserve a spot too, so you can tell whether the RAG actually helped.

Benzer Videolar

The future of AI is open-source. And ollama is the easiest way to build AI applications with open-source LLMs. Here's how to build a free, private RAG app using open-source tools. We'll use: - Ollama for LLMs and embedding models - PostgreSQL for data storage and retrieval - pgai Vectorizer for embedding creation and sync (I use Nomic for embeddings and tinnyllama as my LLM but you can substitute them for any models on Ollama)
15:16

The future of AI is open-source. And ollama is the easiest way to build AI applications with open-source LLMs. Here's how to build a free, private RAG app using open-source tools. We'll use: - Ollama for LLMs and embedding models - PostgreSQL for data storage and retrieval - pgai Vectorizer for embedding creation and sync (I use Nomic for embeddings and tinnyllama as my LLM but you can substitute them for any models on Ollama)

Avthar

34,261 görüntüleme • 1 yıl önce

Understanding LLMs by Building One 👉 We use large language models every day, but what actually happens inside them?
1:24

Understanding LLMs by Building One 👉 We use large language models every day, but what actually happens inside them?

Danilo Poccia

15,053 görüntüleme • 6 ay önce

Soatto vs LeCun: Are LLMs World Models?🧐
1:50

Soatto vs LeCun: Are LLMs World Models?🧐

Ravid Shwartz Ziv

14,840 görüntüleme • 7 ay önce

Watch "Endless experimentation: Building AI models in the wild." This is a 50-minute, MIT lecture about problems when deploying models and LLMs in the real world and how to prepare to solve them. This is a great lecture for those building production machine learning.
54:56

Watch "Endless experimentation: Building AI models in the wild." This is a 50-minute, MIT lecture about problems when deploying models and LLMs in the real world and how to prepare to solve them. This is a great lecture for those building production machine learning.

Santiago

117,341 görüntüleme • 2 yıl önce

🚀Build your AI engineering skills at AI Dev NYC: knowledge graphs, agent memory, harnesses, self-improving agents, inference and security. Plus a fireside chat with Andrew Ng and Yann LeCun on world models. 📅Nov 30–Dec 1 · Chelsea Piers, NYC
0:38

🚀Build your AI engineering skills at AI Dev NYC: knowledge graphs, agent memory, harnesses, self-improving agents, inference and security. Plus a fireside chat with Andrew Ng and Yann LeCun on world models. 📅Nov 30–Dec 1 · Chelsea Piers, NYC

DeepLearning.AI

82,006 görüntüleme • 7 gün önce

World models that aren't grounded in the real world will never reach their potential for physical AI. 🌎 Just as RAG cut hallucination in LLMs, location-specific grounding lets robots choose the right action in the right place. Read more about Niantic Spatial’s thinking: #WorldModels #PhysicalAI #AI #EmbodiedAI #SpatialAI #Robotics
0:31

World models that aren't grounded in the real world will never reach their potential for physical AI. 🌎 Just as RAG cut hallucination in LLMs, location-specific grounding lets robots choose the right action in the right place. Read more about Niantic Spatial’s thinking: #WorldModels #PhysicalAI #AI #EmbodiedAI #SpatialAI #Robotics

Niantic Spatial 🌎

34,745 görüntüleme • 1 ay önce

I am mostly talking to integrators andConsultant Engineers in AI, bot every institution requires general purpose chatbots like ChatGPT or claude some of you need a good RAG system with good embedding models , its not a resources consumption issue it is an accuracy problem
7:13

I am mostly talking to integrators andConsultant Engineers in AI, bot every institution requires general purpose chatbots like ChatGPT or claude some of you need a good RAG system with good embedding models , its not a resources consumption issue it is an accuracy problem

Dipl. Ing MkenyaDaima | Bongani | Mamba |

26,260 görüntüleme • 2 ay önce

Building Vertical AI models explained
2:47

Building Vertical AI models explained

Vertical AI

112,385 görüntüleme • 1 yıl önce

Plexe AI (Plexe AI) is building an open-source agent to build ML models from a prompt. Their agent is already helping companies go from idea to deployed models 10x faster. Congrats on the launch, Vaibhav Dubey and Marcello De Bernardi!
0:46

Plexe AI (Plexe AI) is building an open-source agent to build ML models from a prompt. Their agent is already helping companies go from idea to deployed models 10x faster. Congrats on the launch, Vaibhav Dubey and Marcello De Bernardi!

Y Combinator

55,905 görüntüleme • 1 yıl önce

DeepSeek RAG Agent : 100% Local using ollama Code below 👇 💡 RAG AI Agent with Reasoning DeepSeek 🌐 Local using @Ollama ✨ Few lines of Code PraisonAI 🔍 UI using Streamlit 💪 Nomic Embed Text for embedding 🧠 Deep Contextual Awareness
7:24

DeepSeek RAG Agent : 100% Local using ollama Code below 👇 💡 RAG AI Agent with Reasoning DeepSeek 🌐 Local using @Ollama ✨ Few lines of Code PraisonAI 🔍 UI using Streamlit 💪 Nomic Embed Text for embedding 🧠 Deep Contextual Awareness

Mervin Praison

59,840 görüntüleme • 1 yıl önce

Run AI Models (LLMs) from USB Flash Drive | No Install, Fully Offline Enjoy
4:57

Run AI Models (LLMs) from USB Flash Drive | No Install, Fully Offline Enjoy

The Cybersecurity guy

54,330 görüntüleme • 1 ay önce

Why LLMs are a dead end for human-level intelligence, and especially for Physical AI / Robotics. The next leap isn’t bigger language models. It’s World Models. I just dropped a full 1-hour presentation from Shanghai: “World Models: the ChatGPT moment for robotics?” → Why LLMs hit a wall → Why action-conditioned world models planning in latent space are the real path → Live World Forge demo with LeWorldModel + Hugging Face LeRobot Watch here. The future of intelligence is embodied, not just chatty.
1:16:13

Why LLMs are a dead end for human-level intelligence, and especially for Physical AI / Robotics. The next leap isn’t bigger language models. It’s World Models. I just dropped a full 1-hour presentation from Shanghai: “World Models: the ChatGPT moment for robotics?” → Why LLMs hit a wall → Why action-conditioned world models planning in latent space are the real path → Live World Forge demo with LeWorldModel + Hugging Face LeRobot Watch here. The future of intelligence is embodied, not just chatty.

abdel

39,459 görüntüleme • 4 ay önce

Hiring RL Engineer! Started off as a curious project at Lossfunk to push the boundaries of LLMs in social reasoning - we are now building RL environments, data, and benchmarks to simulate more real-world scenarios. If you want to train SoTA RL models over multi-GPUs (H200s/B200s) to unlock next AI frontier, this is for you.
1:21

Hiring RL Engineer! Started off as a curious project at Lossfunk to push the boundaries of LLMs in social reasoning - we are now building RL environments, data, and benchmarks to simulate more real-world scenarios. If you want to train SoTA RL models over multi-GPUs (H200s/B200s) to unlock next AI frontier, this is for you.

Satpal Singh Rathore

46,010 görüntüleme • 1 yıl önce

7 UI skills every design engineer should know when building with AI agents: 1. emil-design-eng 2. make-interfaces-feel-better 3. playwright-cli 4. react-doctor 5. fixing-accessibility 6. 12-principles-of-animation 7. shadcn
0:34

7 UI skills every design engineer should know when building with AI agents: 1. emil-design-eng 2. make-interfaces-feel-better 3. playwright-cli 4. react-doctor 5. fixing-accessibility 6. 12-principles-of-animation 7. shadcn

Nero

43,535 görüntüleme • 1 ay önce

Building AI ecosystem in India - Common compute capacity: 34,000+ GPUs - Techno-legal AI regulation - Indigenous LLMs & sectoral models - Nurturing AI talent pipeline 📍St. Petersburg International Economic Forum 2025, Russia
1:53

Building AI ecosystem in India - Common compute capacity: 34,000+ GPUs - Techno-legal AI regulation - Indigenous LLMs & sectoral models - Nurturing AI talent pipeline 📍St. Petersburg International Economic Forum 2025, Russia

Ashwini Vaishnaw

30,558 görüntüleme • 1 yıl önce

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people are still treating LLMs like chatbots. Karpathy is showing the full stack: Memory → Vision → Reasoning → Search → Tools Prompting is the old workflow. Agentic systems are the new one. This 40-minute talk is worth more than most paid AI agent courses. Bookmark and watch it before everyone catches up. Then read how to turn LLMs into self-improving agent loops below
42:43

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people are still treating LLMs like chatbots. Karpathy is showing the full stack: Memory → Vision → Reasoning → Search → Tools Prompting is the old workflow. Agentic systems are the new one. This 40-minute talk is worth more than most paid AI agent courses. Bookmark and watch it before everyone catches up. Then read how to turn LLMs into self-improving agent loops below

Lunar

356,880 görüntüleme • 2 ay önce

Every Engineer should know these letters. 😅
0:38

Every Engineer should know these letters. 😅

CURIOSITY DOSE 🧠

300,603 görüntüleme • 16 gün önce

Every Engineer should know these letters 😅
0:38

Every Engineer should know these letters 😅

Nikita Rai

5,895,618 görüntüleme • 18 gün önce