正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

We’re open-sourcing a new tool to control how LLMs behave: k-steering. In just 10 lines of code, you can control multiple aspects of LLM behavior at the same time without any fine-tuning or prompt engineering. Here's how 👇

Martian

3,600 subscribers

13,062 次观看 • 4 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

Andrew Ng

502,866 次观看 • 3 年前

Prompt engineering just leveled up You can now create your own Prompt Versioning System without writing a single line of code Here’s how ↓

Prompt engineering just leveled up You can now create your own Prompt Versioning System without writing a single line of code Here’s how ↓

Nelly;

36,081 次观看 • 10 个月前

Learn a development pattern to systematically improve the accuracy and reliability of LLM applications in our new short course, Improving Accuracy of LLM Applications, built in partnership with Lamini and Meta, and taught by Lamini’s CEO Sharon Zhou, and Meta’s Senior Director of Partner Engineering, Amit Sangani. (Disclosure: I am an investor in Lamini.) The path to tuning an LLM application can be complex. In this course, you'll learn a systematic sequence of steps for improving accuracy by reducing hallucinations: - Create an evaluation dataset to measure model accuracy - Add prompt engineering and self-reflection - Fine-tune your model including "memory-tuning" which is a new method of embedding facts in an LLM Using the Llama 3-8B parameter model, you will: - Build a text-to-SQL agent with a custom schema and simulate situations where it hallucinates - Understand the difference between instruction fine-tuning, which gives pre-trained LLMs instructions to follow, and memory fine-tuning - See how Performance-Efficient Fine-tuning (PEFT) techniques like Low-Rank Adaptation (LoRA) reduce training time by 100x and Mixture of Memory Experts (MoME) reduces it even further I appreciate Meta releasing the Llama's family of open models -- this course gives an example of the unique type of work that developers can do with such models. Please sign up here:

Learn a development pattern to systematically improve the accuracy and reliability of LLM applications in our new short course, Improving Accuracy of LLM Applications, built in partnership with Lamini and Meta, and taught by Lamini’s CEO Sharon Zhou, and Meta’s Senior Director of Partner Engineering, Amit Sangani. (Disclosure: I am an investor in Lamini.) The path to tuning an LLM application can be complex. In this course, you'll learn a systematic sequence of steps for improving accuracy by reducing hallucinations: - Create an evaluation dataset to measure model accuracy - Add prompt engineering and self-reflection - Fine-tune your model including "memory-tuning" which is a new method of embedding facts in an LLM Using the Llama 3-8B parameter model, you will: - Build a text-to-SQL agent with a custom schema and simulate situations where it hallucinates - Understand the difference between instruction fine-tuning, which gives pre-trained LLMs instructions to follow, and memory fine-tuning - See how Performance-Efficient Fine-tuning (PEFT) techniques like Low-Rank Adaptation (LoRA) reduce training time by 100x and Mixture of Memory Experts (MoME) reduces it even further I appreciate Meta releasing the Llama's family of open models -- this course gives an example of the unique type of work that developers can do with such models. Please sign up here:

Andrew Ng

66,435 次观看 • 2 年前

With the new scrambleText() feature, you can control reveal direction, create cursor effects, apply perturbation and easing, and chain it in keyframes and timelines like any other Anime.js animation property. It's crazy how just a few lines of code can create such visually complex effects.

With the new scrambleText() feature, you can control reveal direction, create cursor effects, apply perturbation and easing, and chain it in keyframes and timelines like any other Anime.js animation property. It's crazy how just a few lines of code can create such visually complex effects.

Julian Garnier

133,069 次观看 • 3 个月前

You can achieve this smooth, native number transition using Expo-ui with just a few lines of code. All without writing a single line of native code! 🚀 Here is how you can do it 👇

You can achieve this smooth, native number transition using Expo-ui with just a few lines of code. All without writing a single line of native code! 🚀 Here is how you can do it 👇

Hewad Mubariz

61,263 次观看 • 5 个月前

i built a tool that lets you clone ANY video with AI saw a movie scene you want to recreate? a commercial? a music video? just upload it to this tool and get the exact structured prompt to generate it in sora 2 you no longer need to guess how to describe what you want to generate. show the tool the reference and it engineers the prompt for you. the tool analyzes: - camera movements and angles - lighting and color grading - scene composition and timing then converts everything into sora-optimized prompt structure this is how you recreate any visual style without prompt engineering experience RT + reply 'TOOL' and i'll send you access (must follow so i can dm)

i built a tool that lets you clone ANY video with AI saw a movie scene you want to recreate? a commercial? a music video? just upload it to this tool and get the exact structured prompt to generate it in sora 2 you no longer need to guess how to describe what you want to generate. show the tool the reference and it engineers the prompt for you. the tool analyzes: - camera movements and angles - lighting and color grading - scene composition and timing then converts everything into sora-optimized prompt structure this is how you recreate any visual style without prompt engineering experience RT + reply 'TOOL' and i'll send you access (must follow so i can dm)

Miko

43,075 次观看 • 10 个月前

Excited to present the LLM-Council skill. Initial idea by Karpathy. I just packaged it as a skill. You can easily spin up a council of LLMs or agents via Fireworks. Watch how the new GLM-5 model "deliberates" on other LLMs' thoughts on the big question, "Can LLMs reason?" Things worth paying attention to: New open models like GLM-5 have surprisingly improved on complex reasoning and long-running agentic tasks. The AskUserQuestion tool in Claude Code came in handy to select the council and chairperson. As Andrej Karpathy puts it, it's a really interesting way to get different perspectives from LLMs, which can lead to better decision-making on whatever task you are working on. You can use it for other agentic coding use cases, like evaluation, tool building, designing, and research.

Excited to present the LLM-Council skill. Initial idea by Karpathy. I just packaged it as a skill. You can easily spin up a council of LLMs or agents via Fireworks. Watch how the new GLM-5 model "deliberates" on other LLMs' thoughts on the big question, "Can LLMs reason?" Things worth paying attention to: New open models like GLM-5 have surprisingly improved on complex reasoning and long-running agentic tasks. The AskUserQuestion tool in Claude Code came in handy to select the council and chairperson. As Andrej Karpathy puts it, it's a really interesting way to get different perspectives from LLMs, which can lead to better decision-making on whatever task you are working on. You can use it for other agentic coding use cases, like evaluation, tool building, designing, and research.

elvis

39,593 次观看 • 6 个月前

View Transitions just learned how to multitask with the rest of the page. Scoped View Transitions let you run multiple, fluid transitions at the same time, all with just a few lines of CSS. Web UX, re-imagined →

View Transitions just learned how to multitask with the rest of the page. Scoped View Transitions let you run multiple, fluid transitions at the same time, all with just a few lines of CSS. Web UX, re-imagined →

Chrome for Developers

114,634 次观看 • 8 个月前

Triple inverted pendulum in transition control A classic control problem, done in real time. This setup moves smoothly between all eight equilibrium points of a triple inverted pendulum. The system reacts every 1 millisecond, which shows how fast modern control loops can be. • Real-time control at 1 ms sampling • Stable transitions between multiple balance points • Built with Simulink and LW-RCP02 hardware This is a beautiful example of how theory meets practice in advanced control engineering. Video: Credit: Embedded Control Lab, Inha University —- Weekly robotics and AI insights. Subscribe free:

Triple inverted pendulum in transition control A classic control problem, done in real time. This setup moves smoothly between all eight equilibrium points of a triple inverted pendulum. The system reacts every 1 millisecond, which shows how fast modern control loops can be. • Real-time control at 1 ms sampling • Stable transitions between multiple balance points • Built with Simulink and LW-RCP02 hardware This is a beautiful example of how theory meets practice in advanced control engineering. Video: Credit: Embedded Control Lab, Inha University —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

168,101 次观看 • 7 个月前

You can now clone any website just by writing a prompt. Simply add the new Firecrawl MCP server to your favorite AI coding tool for improved web data extraction, and let Claude code it for you. Here’s how:

You can now clone any website just by writing a prompt. Simply add the new Firecrawl MCP server to your favorite AI coding tool for improved web data extraction, and let Claude code it for you. Here’s how:

Alvaro Cintas

540,189 次观看 • 1 年前

PROPAGANDA AND SOCIAL ENGINEERING TECHNIQUES A complete breakdown of all social engineering and propaganda techniques used to shape your way of thinking and/or behavior. Those that war against your mind have spent many decades perfecting how to manipulate and control you.

PROPAGANDA AND SOCIAL ENGINEERING TECHNIQUES A complete breakdown of all social engineering and propaganda techniques used to shape your way of thinking and/or behavior. Those that war against your mind have spent many decades perfecting how to manipulate and control you.

Redpill Drifter

116,366 次观看 • 6 个月前

Learn how to build an optimized LLM inference system from the ground up in our new short course, Efficiently Serving LLMs, built in collaboration with Predibase by Rubrik and taught by Travis Addair. Whether you're serving your own LLM or using a model hosting service, this course will give you a deep understanding of the optimizations required to efficiently serve many users at once. - Learn how LLMs generate text one token at a time, and how techniques like KV caching, continuous batching, and quantization speed things up and optimize memory usage for serving multiple users. - Benchmark the performance of these LLM optimizations to explore the trade-offs between quickly responding to an individual user’s request vs. serving many users at once. - Use techniques like low-rank adaptation (LoRA) to efficiently serve hundreds of unique, custom fine-tuned models on a single device, without sacrificing throughput. - Use Predibase's LoRAX framework to see optimization techniques in action on a real LLM server. Sign up here:

Learn how to build an optimized LLM inference system from the ground up in our new short course, Efficiently Serving LLMs, built in collaboration with Predibase by Rubrik and taught by Travis Addair. Whether you're serving your own LLM or using a model hosting service, this course will give you a deep understanding of the optimizations required to efficiently serve many users at once. - Learn how LLMs generate text one token at a time, and how techniques like KV caching, continuous batching, and quantization speed things up and optimize memory usage for serving multiple users. - Benchmark the performance of these LLM optimizations to explore the trade-offs between quickly responding to an individual user’s request vs. serving many users at once. - Use techniques like low-rank adaptation (LoRA) to efficiently serve hundreds of unique, custom fine-tuned models on a single device, without sacrificing throughput. - Use Predibase's LoRAX framework to see optimization techniques in action on a real LLM server. Sign up here:

Andrew Ng

104,727 次观看 • 2 年前

New Course: Reinforcement Fine-Tuning LLMs with GRPO! Learn to use reinforcement learning to improve your LLM performance in this short course, built in collaboration with Predibase by Rubrik, and taught by Travis Addair, its Co-Founder and CTO, and Arnav Garg, its Senior Engineer and Machine Learning Lead. Reasoning models have been one of the most important developments in LLMs. Reinforcement Fine-Tuning (RFT) uses rewards to encourage LLMs to find solutions to multi-step reasoning tasks such as solving math problems and debugging code - without needing pre-existing training examples like in traditional supervised fine-tuning. Group Relative Policy Optimization (GRPO) is a reinforcement fine-tuning algorithm gaining rapid adoption. Developed by the DeepSeek team and used to train the R1 reasoning model, GRPO uses reward functions that you can write in Python to assign rewards to model responses. It’s beneficial for tasks with verifiable outcomes and can work well even with fewer than 100 training examples. It can also significantly improve the reasoning ability of smaller LLMs, making applications faster and more cost effective. In this course, you’ll take a technical deep dive into RFT with GRPO. You’ll learn to build reward functions that you can use in the GRPO training process to guide an LLM toward better performance on multi-step reasoning tasks. In detail, you’ll: - Learn when reinforcement fine-tuning is a better fit than supervised fine-tuning, especially for tasks involving multi-step reasoning or limited labeled data. - Understand how GRPO uses programmable reward functions as a more scalable alternative to the human feedback required for other reinforcement learning algorithms, such as RLHF and DPO. - Frame the Wordle game as a reinforcement fine-tuning problem and see how an LLM can learn to plan, analyze feedback, and improve its strategy over time. - Design reward functions that power the reinforcement fine-tuning process. - Learn techniques for evaluating more subjective tasks, such as rating the quality of a text summary, using an LLM as a judge. - Understand why reward hacking happens and how to avoid it by adding penalty functions to discourage undesirable behaviors. - Learn the four key components of the loss calculation in the GRPO algorithm: token probability distribution ratios, advantages, clipping, and KL-divergence. - Launch reinforcement fine-tuning jobs using Predibase’s hosted training services. By the end of this course, you’ll be able to build and fine-tune LLMs using reinforcement learning to improve reasoning without relying on large labeled datasets or subjective human feedback. Please sign up here:

New Course: Reinforcement Fine-Tuning LLMs with GRPO! Learn to use reinforcement learning to improve your LLM performance in this short course, built in collaboration with Predibase by Rubrik, and taught by Travis Addair, its Co-Founder and CTO, and Arnav Garg, its Senior Engineer and Machine Learning Lead. Reasoning models have been one of the most important developments in LLMs. Reinforcement Fine-Tuning (RFT) uses rewards to encourage LLMs to find solutions to multi-step reasoning tasks such as solving math problems and debugging code - without needing pre-existing training examples like in traditional supervised fine-tuning. Group Relative Policy Optimization (GRPO) is a reinforcement fine-tuning algorithm gaining rapid adoption. Developed by the DeepSeek team and used to train the R1 reasoning model, GRPO uses reward functions that you can write in Python to assign rewards to model responses. It’s beneficial for tasks with verifiable outcomes and can work well even with fewer than 100 training examples. It can also significantly improve the reasoning ability of smaller LLMs, making applications faster and more cost effective. In this course, you’ll take a technical deep dive into RFT with GRPO. You’ll learn to build reward functions that you can use in the GRPO training process to guide an LLM toward better performance on multi-step reasoning tasks. In detail, you’ll: - Learn when reinforcement fine-tuning is a better fit than supervised fine-tuning, especially for tasks involving multi-step reasoning or limited labeled data. - Understand how GRPO uses programmable reward functions as a more scalable alternative to the human feedback required for other reinforcement learning algorithms, such as RLHF and DPO. - Frame the Wordle game as a reinforcement fine-tuning problem and see how an LLM can learn to plan, analyze feedback, and improve its strategy over time. - Design reward functions that power the reinforcement fine-tuning process. - Learn techniques for evaluating more subjective tasks, such as rating the quality of a text summary, using an LLM as a judge. - Understand why reward hacking happens and how to avoid it by adding penalty functions to discourage undesirable behaviors. - Learn the four key components of the loss calculation in the GRPO algorithm: token probability distribution ratios, advantages, clipping, and KL-divergence. - Launch reinforcement fine-tuning jobs using Predibase’s hosted training services. By the end of this course, you’ll be able to build and fine-tune LLMs using reinforcement learning to improve reasoning without relying on large labeled datasets or subjective human feedback. Please sign up here:

Andrew Ng

86,622 次观看 • 1 年前

We’re applying to the Pump.fun Build in Public Hackathon. We're building Clovr. An AI tool that turns ideas into real Next.js frontends. No more boilerplate. No more blank files. Just clean, ready-to-use, beautiful code you can export or open straight in a GitHub repo. We’re building the future of how frontends are built.

We’re applying to the Pump.fun Build in Public Hackathon. We're building Clovr. An AI tool that turns ideas into real Next.js frontends. No more boilerplate. No more blank files. Just clean, ready-to-use, beautiful code you can export or open straight in a GitHub repo. We’re building the future of how frontends are built.

Alby Churven

24,523 次观看 • 6 个月前

🚨 JUST IN: Republicans are now seriously questioning if Rep. Jasmine Crockett (D-TX) has any knowledge of civics whatsoever after she claimed Republicans "CONTROL EVERYTHING" in the Senate and can reopen the government at any time. They need *60* votes... "Republicans don't know how to COUNT. Here's the thing. When you're in a legislative body, you control EVERYTHING. When the government shuts down, it's on Y'ALL."

🚨 JUST IN: Republicans are now seriously questioning if Rep. Jasmine Crockett (D-TX) has any knowledge of civics whatsoever after she claimed Republicans "CONTROL EVERYTHING" in the Senate and can reopen the government at any time. They need 60 votes... "Republicans don't know how to COUNT. Here's the thing. When you're in a legislative body, you control EVERYTHING. When the government shuts down, it's on Y'ALL."

Eric Daugherty

843,710 次观看 • 10 个月前

Learn to train an LLM with distributed data while ensuring privacy using federated learning in a new two-part short course, Intro to Federated Learning and Federated Fine-tuning of LLMs with Private Data, created with Flower and taught by Daniel J. Beutel and Nicholas Lane. Federated learning allows a single model to be trained across multiple devices, such as phones, or multiple organizations, such as hospitals, without the need to share data to a central server. This two-part course gives you an introduction to federated learning, and then teaches you how to fine-tune your large language model with distributed data using Flower Lab’s open source federated learning framework. You’ll learn: - How to use federated learning to train a variety of models, ranging from speech and vision models to LLMs, across distributed data while offering data privacy options to users and organizations. - Privacy Enhancing Technologies like differential privacy (DP), which obscures individual data by adding calibrated noise to query results. - Two variants of differential privacy - Central and Local - and how to choose depending on your use case. - How to measure and decrease bandwidth usage to make federated learning more practical and efficient with techniques like using pre-trained models and Parameter-Efficient Fine-Tuning - How federated LLM fine-tuning reduces the risk of leaking training data. Sign up here!

Learn to train an LLM with distributed data while ensuring privacy using federated learning in a new two-part short course, Intro to Federated Learning and Federated Fine-tuning of LLMs with Private Data, created with Flower and taught by Daniel J. Beutel and Nicholas Lane. Federated learning allows a single model to be trained across multiple devices, such as phones, or multiple organizations, such as hospitals, without the need to share data to a central server. This two-part course gives you an introduction to federated learning, and then teaches you how to fine-tune your large language model with distributed data using Flower Lab’s open source federated learning framework. You’ll learn: - How to use federated learning to train a variety of models, ranging from speech and vision models to LLMs, across distributed data while offering data privacy options to users and organizations. - Privacy Enhancing Technologies like differential privacy (DP), which obscures individual data by adding calibrated noise to query results. - Two variants of differential privacy - Central and Local - and how to choose depending on your use case. - How to measure and decrease bandwidth usage to make federated learning more practical and efficient with techniques like using pre-trained models and Parameter-Efficient Fine-Tuning - How federated LLM fine-tuning reduces the risk of leaking training data. Sign up here!

Andrew Ng

64,609 次观看 • 2 年前

A brand new AI tool just dropped. Mirage studio by captions lets you create cinematic videos without actors, cameras, or editors. The future of video content is here. Here's how it works:

Future Stacked

143,949 次观看 • 1 年前

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:

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 次观看 • 10 个月前