Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

A little video that - explains the relationship between conventional LLMs and reasoning models (and agents), - philosophizes a about "from scratch" approaches, - and explains how to install Python & PyTorch requirements with uv.

Sebastian Raschka

500,285 subscribers

56,522 views • 5 days ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Is this the real reason the #Bitcoin logo is that distinct shade of orange? And does this theory reveal a hidden relationship between Bitcoin and Ripple? 🤯 An excerpt from my latest video explains my reasoning… #NFAResearchGroup

NotFinancialAdvice.Crypto

257,321 views • 1 year ago

This video literally explains how to use AI (Claude & ChatGPT) to build a profitable personal brand from scratch:

Mubbu

168,863 views • 1 year ago

Jynxzi cries & explains how he used to stalk girls and watch P*rn while in a relationship with Breckie Hill.. 😳

Sensitive content

Jynxzi cries & explains how he used to stalk girls and watch P*rn while in a relationship with Breckie Hill.. 😳

clip 🛸

595,265 views • 2 years ago

The legendary Subbarao Kambhampati (కంభంపాటి సుబ్బారావు) explains the difference between reasoning and memorisation using the example of the famous "why are manhole covers round?" interview question. Which do you think LLMs do?

The legendary Subbarao Kambhampati (కంభంపాటి సుబ్బారావు) explains the difference between reasoning and memorisation using the example of the famous "why are manhole covers round?" interview question. Which do you think LLMs do?

Machine Learning Street Talk

326,897 views • 2 years ago

PyTorch 2.13 brings FlexAttention to Apple Silicon, cuts peak memory by up to 4× for large-vocabulary models with nn.LinearCrossEntropyLoss, and updates distributed training, compilation, profiling, and on-device inference. Our live Q&A examined CUDA version support, CuTeDSL in TorchInductor, Python 3.15, ExecuTorch, torch.compile, and plans for PyTorch 2.14. Andrey Talman (Meta), albanD (Meta), and Piotr Bialecki (NVIDIA) joined moderator Chris Gottbrath (Gottbrath Technologies). This clip explains how FlexAttention compiles kernels specialized for the requested masking pattern, allowing them to skip unnecessary computation. It also covers speedups of up to approximately 12× over SDPA in tested sparse configurations and a deterministic backward path on CUDA that removes one source of nondeterminism in gradient computation. 🔗 Watch the full PyTorch 2.13 Release Live Q&A:

PyTorch 2.13 brings FlexAttention to Apple Silicon, cuts peak memory by up to 4× for large-vocabulary models with nn.LinearCrossEntropyLoss, and updates distributed training, compilation, profiling, and on-device inference. Our live Q&A examined CUDA version support, CuTeDSL in TorchInductor, Python 3.15, ExecuTorch, torch.compile, and plans for PyTorch 2.14. Andrey Talman (Meta), albanD (Meta), and Piotr Bialecki (NVIDIA) joined moderator Chris Gottbrath (Gottbrath Technologies). This clip explains how FlexAttention compiles kernels specialized for the requested masking pattern, allowing them to skip unnecessary computation. It also covers speedups of up to approximately 12× over SDPA in tested sparse configurations and a deterministic backward path on CUDA that removes one source of nondeterminism in gradient computation. 🔗 Watch the full PyTorch 2.13 Release Live Q&A:

PyTorch

18,591 views • 1 month ago

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

61,391 views • 1 year ago

Ilya Sutskever: “My document gently flowed to where AI is today - and agents are the future” He wrote the paper that made LLMs like Claude and ChatGPT possible - and explains it from scratch in 20 minutes Never touched AI or use it every day - you need to watch this course Watch - bookmark, then put the entire lecture into practice with the article below ↓

Ilya Sutskever: “My document gently flowed to where AI is today - and agents are the future” He wrote the paper that made LLMs like Claude and ChatGPT possible - and explains it from scratch in 20 minutes Never touched AI or use it every day - you need to watch this course Watch - bookmark, then put the entire lecture into practice with the article below ↓

codila

49,696 views • 19 days ago

A CIA agent explains how they CREATE sleeper agents by isolating and training them from birth to become SPIES 😳👀

A CIA agent explains how they CREATE sleeper agents by isolating and training them from birth to become SPIES 😳👀

Killa 🌺

201,149 views • 7 months ago

High-net-worth divorce attorney Jacqueline Newman explains the math behind ultrarich divorce. Divorce between wealthy couples can involve a complex web of assets and millions in annual spending. Newman explains how she approaches these cases. 🎥

High-net-worth divorce attorney Jacqueline Newman explains the math behind ultrarich divorce. Divorce between wealthy couples can involve a complex web of assets and millions in annual spending. Newman explains how she approaches these cases. 🎥

The Wall Street Journal

108,887 views • 4 months ago

NVIDIA released a video showing their new Alpamayo In-Car Reasoning Model. An AI that explains decisions, responds to passengers, and drives. How it works: • Verbalized Reasoning: In complex situations, the car selectively explains its reasoning aloud, giving passengers insight into the Al's decisions and helping to build trust. • Natural Language Q&A: Riders can ask questions about the car's behavior or the surrounding environment, and Alpamayo responds in real time. • Language Instructions and Commands: Passengers can request actions such as changing lanes, speeding up, taking a detour, or pulling over, and Alpamayo performs them naturally.

NVIDIA released a video showing their new Alpamayo In-Car Reasoning Model. An AI that explains decisions, responds to passengers, and drives. How it works: • Verbalized Reasoning: In complex situations, the car selectively explains its reasoning aloud, giving passengers insight into the Al's decisions and helping to build trust. • Natural Language Q&A: Riders can ask questions about the car's behavior or the surrounding environment, and Alpamayo responds in real time. • Language Instructions and Commands: Passengers can request actions such as changing lanes, speeding up, taking a detour, or pulling over, and Alpamayo performs them naturally.

Nic Cruz Patane

87,841 views • 5 months ago

Anyone outwith Scotland wondering why there was so little scrutiny of this story should watch this video filmed and published by STV News on Facebook in 2020. It explains a lot about the relationship between the former first minister and those who should have held her to account.

Anyone outwith Scotland wondering why there was so little scrutiny of this story should watch this video filmed and published by STV News on Facebook in 2020. It explains a lot about the relationship between the former first minister and those who should have held her to account.

Gethin Chamberlain

30,381 views • 3 months ago

Demis Hassabis on the next 12 Months: - Full multimodal convergence: Models like Gemini will seamlessly take in and output text, images, audio, and video, with cross-pollination that boosts reasoning + creativity. - Breakthrough visual intelligence: Image models like Nano Banana Pro will produce highly accurate infographics and show near-human visual understanding. - Language + video fusion: Video models integrated with LLMs unlock richer analysis, storytelling, and step-by-step visual reasoning. - World models go mainstream like Genie 3 - Agents become reliable

Demis Hassabis on the next 12 Months: - Full multimodal convergence: Models like Gemini will seamlessly take in and output text, images, audio, and video, with cross-pollination that boosts reasoning + creativity. - Breakthrough visual intelligence: Image models like Nano Banana Pro will produce highly accurate infographics and show near-human visual understanding. - Language + video fusion: Video models integrated with LLMs unlock richer analysis, storytelling, and step-by-step visual reasoning. - World models go mainstream like Genie 3 - Agents become reliable

Chubby♨️

89,236 views • 9 months ago

Melyssa Ford explains the reasoning behind her DDG v Halle take and gets transparent and personal about her dealings with postpartum depression

Melyssa Ford explains the reasoning behind her DDG v Halle take and gets transparent and personal about her dealings with postpartum depression

Micah Jung Un

335,139 views • 1 year ago

Introducing Collaborative Reasoner: a framework to improve collaborative reasoning in language models. Collaborative Reasoner paves the way for developing social agents that can partner with humans and other agents. Read the research paper and download the code.

Introducing Collaborative Reasoner: a framework to improve collaborative reasoning in language models. Collaborative Reasoner paves the way for developing social agents that can partner with humans and other agents. Read the research paper and download the code.

AI at Meta

58,590 views • 1 year ago

Setting up a Python agent shouldn't take all day. Watch how we use uv (the blazing fast package manager written in Rust) to initialize an environment and install the Agent Development Kit instantly →

Setting up a Python agent shouldn't take all day. Watch how we use uv (the blazing fast package manager written in Rust) to initialize an environment and install the Agent Development Kit instantly →

Google Cloud Tech

16,940 views • 2 months ago

🗣️ 'The special relationship that is depicted in the British press between the UK and the U.S. has been over for 40 years.' - Michael Clarke Our military analyst tells Sophy Ridge & Wilfred Frost we have a 'specialist relationship' instead and explains why ⬇️

🗣️ 'The special relationship that is depicted in the British press between the UK and the U.S. has been over for 40 years.' - Michael Clarke Our military analyst tells Sophy Ridge & Wilfred Frost we have a 'specialist relationship' instead and explains why ⬇️

Ridge & Frost

40,213 views • 5 months ago

Katt Williams opens up about his relationship with God on Michelle Obama’s podcast and explains how important building that connection truly is for artists and people ❤️🙏

Katt Williams opens up about his relationship with God on Michelle Obama’s podcast and explains how important building that connection truly is for artists and people ❤️🙏

Killa 🌺

417,500 views • 8 months ago