Loading video...

Video Failed to Load

Go Home

Frontier models that use reasoning to "think" during inference are generating 5X more AI tokens per year. ✨ "Inference is now a thinking process. And in order to teach AI how to think, reinforcement learning and very significant computation was introduced into post-training," said NVIDIA CEO Jensen Huang in...

NVIDIAAIInfra's profile picture

NVIDIA AI Infrastructure

68,650 subscribers

13,329 views • 5 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Anthropic co-founder Jared Kaplan on scaling and the road to human-level AI. At AI Startup School in San Francisco. 00:17 - From Physics to AI 01:41 - Initial Skepticism and Shift to AI 02:12 - AI Training Phases 02:32 - Pre-Training 03:16 - Reinforcement Learning 04:19 - Scaling Laws in Training 08:19 - Unlocking AI Capabilities 11:27 - Organizational Knowledge and Memory 12:19 - Oversight and Nuanced Tasks 13:38 - Preparing for the Future 15:48 - Claude 4 and Beyond 21:18 - Human-AI Collaboration 29:50 - Scaling Laws and Compute Efficiency 35:26 - Audience Q&A
40:47

Anthropic co-founder Jared Kaplan on scaling and the road to human-level AI. At AI Startup School in San Francisco. 00:17 - From Physics to AI 01:41 - Initial Skepticism and Shift to AI 02:12 - AI Training Phases 02:32 - Pre-Training 03:16 - Reinforcement Learning 04:19 - Scaling Laws in Training 08:19 - Unlocking AI Capabilities 11:27 - Organizational Knowledge and Memory 12:19 - Oversight and Nuanced Tasks 13:38 - Preparing for the Future 15:48 - Claude 4 and Beyond 21:18 - Human-AI Collaboration 29:50 - Scaling Laws and Compute Efficiency 35:26 - Audience Q&A

Y Combinator

116,444 views • 11 months ago

As AI labs race to train and deploy new frontier models, existing models become more affordable with better tokenomics. ✨ "Everybody's trying to get to the next frontier. And every time they get to the next frontier, the last generation AI tokens, the cost starts to decline about a factor of 10x every year," said NVIDIA CEO Jensen Huang in a recent keynote. Model optimization techniques such as speculative decoding and multi-token prediction, combined with inference serving platforms like NVIDIA Dynamo on NVIDIA Blackwell NVL72 systems, enable AI factories to boost throughput by 10x with one-tenth of the cost per token. Learn more about AI factory tokenomics ➡️
0:45

As AI labs race to train and deploy new frontier models, existing models become more affordable with better tokenomics. ✨ "Everybody's trying to get to the next frontier. And every time they get to the next frontier, the last generation AI tokens, the cost starts to decline about a factor of 10x every year," said NVIDIA CEO Jensen Huang in a recent keynote. Model optimization techniques such as speculative decoding and multi-token prediction, combined with inference serving platforms like NVIDIA Dynamo on NVIDIA Blackwell NVL72 systems, enable AI factories to boost throughput by 10x with one-tenth of the cost per token. Learn more about AI factory tokenomics ➡️

NVIDIA AI

16,053 views • 5 months ago

"The inflection point for inference has arrived." — Jensen Huang, Founder & CEO of NVIDIA We’ve officially crossed a new milestone in the inference era — where widespread adoption of AI shifts from learning to doing. The breakthrough: extreme codesign across hardware and software driving down cost per token. Lower cost → more inference More inference → more users and applications More users and applications → exponential AI revenue growth
0:41

"The inflection point for inference has arrived." — Jensen Huang, Founder & CEO of NVIDIA We’ve officially crossed a new milestone in the inference era — where widespread adoption of AI shifts from learning to doing. The breakthrough: extreme codesign across hardware and software driving down cost per token. Lower cost → more inference More inference → more users and applications More users and applications → exponential AI revenue growth

NVIDIA

81,834 views • 3 months ago

Training AI to Play Pokemon with Reinforcement Learning by Peter Whidden github: youtube:
1:19

Training AI to Play Pokemon with Reinforcement Learning by Peter Whidden github: youtube:

AK

837,771 views • 2 years ago

Why AI Progress Suddenly Feels Real - my conversation with Yann Dubois, who co-leads the Post-Training Frontiers team at OpenAI 00:00 - Intro 01:30 - Why recent AI progress feels like a step function 04:13 - Model reliability & the emotional rollercoaster of shipping GPT-5.5 07:33 - How OpenAI structures vertical and horizontal teams 09:49 - Improving model efficiency and test-time compute 12:32 - Yann's journey from Switzerland to OpenAI 15:37 - Reasoning in 2026: Real-world utility vs verifiable rewards 18:34 - GPT-5.5 Thinking vs Pro: Scaling test-time compute 20:09 - How reasoning models become more efficient 23:23 - Pre-training scaling and overcoming the data wall 27:03 - Multimodal data, synthetic data, and embodied AI 31:05 - Demystifying mid-training and post-training 37:21 - Does RL create new capabilities in AI? 38:53 - The challenges and frontier of scaling RL 43:09 - Is building AI models a craft or a strict science 48:21 - How AI models generalize across different domains 54:18 - How reinforcement learning cures AI hallucinations 56:04 - Negative generalization and conflicting instructions 58:05 - Can RL scale to law, medicine, and the broader economy? 1:00:19 - The evaluation bottleneck and Model as a Judge 1:04:21 - Continuous AI progress & continual learning 1:08:49 - Will foundation models eat the agent harness 1:11:23 - Why startups should focus on the last mile of AI
1:13:56

Why AI Progress Suddenly Feels Real - my conversation with Yann Dubois, who co-leads the Post-Training Frontiers team at OpenAI 00:00 - Intro 01:30 - Why recent AI progress feels like a step function 04:13 - Model reliability & the emotional rollercoaster of shipping GPT-5.5 07:33 - How OpenAI structures vertical and horizontal teams 09:49 - Improving model efficiency and test-time compute 12:32 - Yann's journey from Switzerland to OpenAI 15:37 - Reasoning in 2026: Real-world utility vs verifiable rewards 18:34 - GPT-5.5 Thinking vs Pro: Scaling test-time compute 20:09 - How reasoning models become more efficient 23:23 - Pre-training scaling and overcoming the data wall 27:03 - Multimodal data, synthetic data, and embodied AI 31:05 - Demystifying mid-training and post-training 37:21 - Does RL create new capabilities in AI? 38:53 - The challenges and frontier of scaling RL 43:09 - Is building AI models a craft or a strict science 48:21 - How AI models generalize across different domains 54:18 - How reinforcement learning cures AI hallucinations 56:04 - Negative generalization and conflicting instructions 58:05 - Can RL scale to law, medicine, and the broader economy? 1:00:19 - The evaluation bottleneck and Model as a Judge 1:04:21 - Continuous AI progress & continual learning 1:08:49 - Will foundation models eat the agent harness 1:11:23 - Why startups should focus on the last mile of AI

Matt Turck

100,493 views • 1 month ago

An exciting new course: Fine-tuning and Reinforcement Learning for LLMs: Intro to Post-training, taught by Sharon Zhou, VP of AI at AMD. Available now at Post-training is the key technique used by frontier labs to turn a base LLM--a model trained on massive unlabeled text to predict the next word/token--into a helpful, reliable assistant that can follow instructions. I've also seen many applications where post-training is what turns a demo application that works only 80% of the time into a reliable system that consistently performs. This course will teach you the most important post-training techniques! In this 5 module course, Sharon walks you through the complete post-training pipeline: supervised fine-tuning, reward modeling, RLHF, and techniques like PPO and GRPO. You'll also learn to use LoRA for efficient training, and to design evals that catch problems before and after deployment. Skills you'll gain: - Apply supervised fine-tuning and reinforcement learning (RLHF, PPO, GRPO) to align models to desired behaviors - Use LoRA for efficient fine-tuning without retraining entire models - Prepare datasets and generate synthetic data for post-training - Understand how to operate LLM production pipelines, with go/no-go decision points and feedback loops These advanced methods aren’t limited to frontier AI labs anymore, and you can now use them in your own applications. Learn here:
2:27

An exciting new course: Fine-tuning and Reinforcement Learning for LLMs: Intro to Post-training, taught by Sharon Zhou, VP of AI at AMD. Available now at Post-training is the key technique used by frontier labs to turn a base LLM--a model trained on massive unlabeled text to predict the next word/token--into a helpful, reliable assistant that can follow instructions. I've also seen many applications where post-training is what turns a demo application that works only 80% of the time into a reliable system that consistently performs. This course will teach you the most important post-training techniques! In this 5 module course, Sharon walks you through the complete post-training pipeline: supervised fine-tuning, reward modeling, RLHF, and techniques like PPO and GRPO. You'll also learn to use LoRA for efficient training, and to design evals that catch problems before and after deployment. Skills you'll gain: - Apply supervised fine-tuning and reinforcement learning (RLHF, PPO, GRPO) to align models to desired behaviors - Use LoRA for efficient fine-tuning without retraining entire models - Prepare datasets and generate synthetic data for post-training - Understand how to operate LLM production pipelines, with go/no-go decision points and feedback loops These advanced methods aren’t limited to frontier AI labs anymore, and you can now use them in your own applications. Learn here:

Andrew Ng

132,304 views • 8 months ago

Open models are accelerating development and deployment across agentic AI, physical AI, and a growing range of industries. ✨ “We have billions of dollars of supercomputers in operation, so we can develop our open models,” said NVIDIA CEO Jensen Huang in a recent keynote. “That work is starting to attract attention across industries worldwide, as we build frontier AI models in many different domains.” This includes leading open models from NVIDIA, including: ⚙️ NVIDIA Nemotron for agentic AI ⚙️ NVIDIA Cosmos and GR00T for physical AI ⚙️ NVIDIA Alpamayo for autonomous vehicles ⚙️ NVIDIA Clara for biomedical AI Learn more about open source and AI ➡️
0:20

Open models are accelerating development and deployment across agentic AI, physical AI, and a growing range of industries. ✨ “We have billions of dollars of supercomputers in operation, so we can develop our open models,” said NVIDIA CEO Jensen Huang in a recent keynote. “That work is starting to attract attention across industries worldwide, as we build frontier AI models in many different domains.” This includes leading open models from NVIDIA, including: ⚙️ NVIDIA Nemotron for agentic AI ⚙️ NVIDIA Cosmos and GR00T for physical AI ⚙️ NVIDIA Alpamayo for autonomous vehicles ⚙️ NVIDIA Clara for biomedical AI Learn more about open source and AI ➡️

NVIDIA AI

19,296 views • 5 months ago

Super excited to launch a new AI course! 🚀 Fine-Tuning & Reinforcement Learning for LLMs: Intro to Post-Training A collaboration between AMD 🤝 Andrew Ng’s DeepLearning.AI to give every developer the tools & compute to work with the same post-training techniques, used across today’s leading AI labs. 🎓 Learn for free → 🧵
0:30

Super excited to launch a new AI course! 🚀 Fine-Tuning & Reinforcement Learning for LLMs: Intro to Post-Training A collaboration between AMD 🤝 Andrew Ng’s DeepLearning.AI to give every developer the tools & compute to work with the same post-training techniques, used across today’s leading AI labs. 🎓 Learn for free → 🧵

Sharon Zhou

20,386 views • 8 months ago

Daniel Kokotajlo says companies are making AI more agentic by scaling RL (reinforcement learning) and connecting agents to various tools. by early 2027, these agents will be fully autonomous, superhuman coders able to replace human programmers.
1:05

Daniel Kokotajlo says companies are making AI more agentic by scaling RL (reinforcement learning) and connecting agents to various tools. by early 2027, these agents will be fully autonomous, superhuman coders able to replace human programmers.

Haider.

11,572 views • 1 year ago

At #LenovoTechWorld @ CES 2026, YY was joined by NVIDIA Founder & CEO Jensen Huang to unveil Lenovo AI Cloud Gigafactory with NVIDIA, scaling AI factories to the gigawatt level to move AI from creation to production in weeks. Learn more:
2:15

At #LenovoTechWorld @ CES 2026, YY was joined by NVIDIA Founder & CEO Jensen Huang to unveil Lenovo AI Cloud Gigafactory with NVIDIA, scaling AI factories to the gigawatt level to move AI from creation to production in weeks. Learn more:

Lenovo

17,170 views • 6 months ago

💡 Inference is hitting a major inflection point in 2025. The future of AI computing will be shaped by who can deliver performance and efficiency at scale. At AMD Advancing AI, Daniel Newman & Patrick Moorhead sat down with Andrew Dieckmann and Anush Elangovan to explore how AMD is strategically positioned to lead in both AI training and inferencing—two of the fastest-growing segments in AI compute. Learn how they're scaling real-world deployments across both training and inference. Catch the full conversation:
0:56

💡 Inference is hitting a major inflection point in 2025. The future of AI computing will be shaped by who can deliver performance and efficiency at scale. At AMD Advancing AI, Daniel Newman & Patrick Moorhead sat down with Andrew Dieckmann and Anush Elangovan to explore how AMD is strategically positioned to lead in both AI training and inferencing—two of the fastest-growing segments in AI compute. Learn how they're scaling real-world deployments across both training and inference. Catch the full conversation:

Six Five Media

29,588 views • 1 year ago

How do AI agents move from simple actions to true reasoning? In Episode 6 of Making a Mind, Dr. Danielle Perszyk and Amazon AI researcher Meiqi Sun explore how reinforcement learning helps AI handle more complex, multistep challenges.
0:57

How do AI agents move from simple actions to true reasoning? In Episode 6 of Making a Mind, Dr. Danielle Perszyk and Amazon AI researcher Meiqi Sun explore how reinforcement learning helps AI handle more complex, multistep challenges.

Amazon News

25,876 views • 4 months ago

Scale CEO Alexandr Wang says AI has "genuinely hit a wall" in terms of pre-training, but there is still progress in AI with evals climbing and models getting smarter due to post-training and test-time compute
1:06

Scale CEO Alexandr Wang says AI has "genuinely hit a wall" in terms of pre-training, but there is still progress in AI with evals climbing and models getting smarter due to post-training and test-time compute

Tsarathustra

193,767 views • 1 year ago

Its nice to see the recent excitement around Q-learning! Here's a clip from a video all about Deep Reinforcement Learning, including Deep Q Learning #machinelearning #ai
2:19

Its nice to see the recent excitement around Q-learning! Here's a clip from a video all about Deep Reinforcement Learning, including Deep Q Learning #machinelearning #ai

Steven Brunton

164,997 views • 2 years ago

At Lenovo Tech World @ CES 2026, YY was joined by NVIDIA Founder & CEO Jensen Huang to unveil Lenovo AI Cloud Gigafactory with NVIDIA, scaling AI factories to the gigawatt level to move AI from creation to production in weeks. Learn more:
2:15

At Lenovo Tech World @ CES 2026, YY was joined by NVIDIA Founder & CEO Jensen Huang to unveil Lenovo AI Cloud Gigafactory with NVIDIA, scaling AI factories to the gigawatt level to move AI from creation to production in weeks. Learn more:

Lenovo

4,370,973 views • 6 months ago

At Lenovo Tech World @ CES 2026, YY was joined by NVIDIA Founder & CEO Jensen Huang to unveil Lenovo AI Cloud Gigafactory with NVIDIA, scaling AI factories to the gigawatt level to move AI from creation to production in weeks. Learn more:
2:15

At Lenovo Tech World @ CES 2026, YY was joined by NVIDIA Founder & CEO Jensen Huang to unveil Lenovo AI Cloud Gigafactory with NVIDIA, scaling AI factories to the gigawatt level to move AI from creation to production in weeks. Learn more:

Lenovo

7,034,091 views • 6 months ago

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:
1:05

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:

DeepLearning.AI

29,369 views • 9 months ago

notes on my reinforcement learning for rocket league side quest so far: i’m in awe that — we live in a time where i can train a reinforcement learning model that is learning to play rocket league and at the same time, test community made rocket league models. where, both processes can run in parallel & locally on my hardware. in the game window — i’m playing against a reinforcement learning ppo model that’s running locally. and in the vscode window — i’m training my own reinforcement learning model (just a dummy example script for now). also, the rocket league botting ecosystem has incredible tooling where you can test out different reinforcement learning ideas against other algorithms + it has great documentation for linux and windows. it’s honestly a beautiful hidden gem of a rabbit hole :)
0:24

notes on my reinforcement learning for rocket league side quest so far: i’m in awe that — we live in a time where i can train a reinforcement learning model that is learning to play rocket league and at the same time, test community made rocket league models. where, both processes can run in parallel & locally on my hardware. in the game window — i’m playing against a reinforcement learning ppo model that’s running locally. and in the vscode window — i’m training my own reinforcement learning model (just a dummy example script for now). also, the rocket league botting ecosystem has incredible tooling where you can test out different reinforcement learning ideas against other algorithms + it has great documentation for linux and windows. it’s honestly a beautiful hidden gem of a rabbit hole :)

naklecha

46,302 views • 1 year ago