Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Most devs think LLM's are only good for producing text. But the real value prop of LLM's is turning raw text/data into structured, searchable objects. If you've never heard of structured outputs, now's your chance:

Matt Pocock

324,392 subscribers

211,861 Aufrufe • vor 11 Monaten •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

New package + paper drop 📄 - Introducing KGGen – a simple library to transform unstructured text into knowledge graphs. Text is abundant, but good knowledge graphs are scarce. Feed it raw text, and KGGen generates a structured network of entities and relationships. (1/7)

New package + paper drop 📄 - Introducing KGGen – a simple library to transform unstructured text into knowledge graphs. Text is abundant, but good knowledge graphs are scarce. Feed it raw text, and KGGen generates a structured network of entities and relationships. (1/7)

Belinda

11,111 Aufrufe • vor 1 Jahr

New Short Course: Getting Structured LLM Output! Learn how to get structured outputs from your LLM applications in this course, built in partnership with .txt, and taught by Will Kurt, a Founding Engineer, and , Developer Relations Engineer. It's challenging for software to automatically parse through an LLM's freeform text outputs. Structured outputs—like JSON—solve this by converting natural language into consistent, clear, data that a machine can read and process. This course teaches you how to generate structured outputs while building several use cases, including a social media analysis agent. You’ll learn about structured outputs and efficient ways to generate outputs in your defined schema or format. You’ll begin by using structured output APIs, then use re-prompting libraries like “instructor” to generate structured output. Finally, you’ll learn how constrained decoding works; this is a very clever technique in which constraints are applied on each subsequent token generated, blocking any tokens that don’t fit your defined schema. In detail, you’ll: - Learn why structured outputs are important, how they allow for scalable software development, and the different approaches to generate them, including vendor-provided APIs, re-prompting libraries, and structured generation. - Build a simple social media agent using OpenAI’s structured output API, learn how to define a model's desired structured output using Pydantic, and perform basic programming with your outputs, such as importing structured data into a data frame using pandas. - Learn how to use the open-source library "instructor," which checks the structured output of the model and re-prompts the model until it validates the desired output, and explore the limitations of this approach. - Understand how structured generation by the “outlines” library works by modifying LLM logits, on a per-generated-token basis based on the desired format, to give a particular output structure. - Learn how regular expressions, which outlines works with, are represented as finite-state machines, and how they can be used to develop a range of structured outputs beyond JSON. By the end of this course, you’ll have broadened your knowledge of the approaches you can use to get structured outputs from your LLM applications. Please sign up here:

New Short Course: Getting Structured LLM Output! Learn how to get structured outputs from your LLM applications in this course, built in partnership with .txt, and taught by Will Kurt, a Founding Engineer, and , Developer Relations Engineer. It's challenging for software to automatically parse through an LLM's freeform text outputs. Structured outputs—like JSON—solve this by converting natural language into consistent, clear, data that a machine can read and process. This course teaches you how to generate structured outputs while building several use cases, including a social media analysis agent. You’ll learn about structured outputs and efficient ways to generate outputs in your defined schema or format. You’ll begin by using structured output APIs, then use re-prompting libraries like “instructor” to generate structured output. Finally, you’ll learn how constrained decoding works; this is a very clever technique in which constraints are applied on each subsequent token generated, blocking any tokens that don’t fit your defined schema. In detail, you’ll: - Learn why structured outputs are important, how they allow for scalable software development, and the different approaches to generate them, including vendor-provided APIs, re-prompting libraries, and structured generation. - Build a simple social media agent using OpenAI’s structured output API, learn how to define a model's desired structured output using Pydantic, and perform basic programming with your outputs, such as importing structured data into a data frame using pandas. - Learn how to use the open-source library "instructor," which checks the structured output of the model and re-prompts the model until it validates the desired output, and explore the limitations of this approach. - Understand how structured generation by the “outlines” library works by modifying LLM logits, on a per-generated-token basis based on the desired format, to give a particular output structure. - Learn how regular expressions, which outlines works with, are represented as finite-state machines, and how they can be used to develop a range of structured outputs beyond JSON. By the end of this course, you’ll have broadened your knowledge of the approaches you can use to get structured outputs from your LLM applications. Please sign up here:

Andrew Ng

89,792 Aufrufe • vor 1 Jahr

Cardinal is a document intelligence platform that turns the trickiest PDFs and scans into structured, LLM-ready data. Most of the world’s data is still locked in PDFs, and after trying every solution and finding none that worked, Harvard + MIT alums Devi and Jianna Liu set out to deliver the high-accuracy outputs LLMs need.

Cardinal is a document intelligence platform that turns the trickiest PDFs and scans into structured, LLM-ready data. Most of the world’s data is still locked in PDFs, and after trying every solution and finding none that worked, Harvard + MIT alums Devi and Jianna Liu set out to deliver the high-accuracy outputs LLMs need.

Y Combinator

43,676 Aufrufe • vor 1 Jahr

Building automations in 10 seconds. Is it really possible? You've heard of no-code automations (useful but takes a while to build) What if you could write text.... And the automation was built on it's own? It's called "text-to-automation" 👇

Building automations in 10 seconds. Is it really possible? You've heard of no-code automations (useful but takes a while to build) What if you could write text.... And the automation was built on it's own? It's called "text-to-automation" 👇

Aadit Sheth

106,150 Aufrufe • vor 3 Jahren

I didn’t write this. I just talked and Typeless transformed my voice into perfectly structured text in seconds. - No keyboard. - No friction. - Just pure ideas, captured as they come. If you think faster than you type, this is your superpower. 👉 Try Typeless: Let your voice do the writing.

I didn’t write this. I just talked and Typeless transformed my voice into perfectly structured text in seconds. - No keyboard. - No friction. - Just pure ideas, captured as they come. If you think faster than you type, this is your superpower. 👉 Try Typeless: Let your voice do the writing.

Parul Gautam

83,262 Aufrufe • vor 8 Monaten

Studies have shown ChatGPT outperforms human annotators for Structured Data by about 25% and costs 30x less. 1 In just 2 months, miners on SN33 running ChatGPT without optimization can’t survive. Today we announce SN33 is now ReadyAI to fully align with our mission 👇 SN33 is building a more performant and significantly cheaper alternative to Scale AI Today structured data is performed primarily by human annotation services like Amazon’s Mechanical Turk and Scale AI It is now more important than ever for every business and individual to make their data AI Ready. However, taking unstructured data and making it Structured Data using today’s tools is extremely costly. SN33 revolutionizes this process, unlocking immense opportunities for commercialization. We lay out the vision for it in this detailed blog post: Validators TODAY can monetize access to this structured data pipeline independently, but we’re streamlining this process, launching a frontend soon that any validator can opt into to provide bandwidth. We've received great feedback from the community, recognizing that what we're building goes far beyond Conversational AI. Building the world's largest annotated conversational dataset (which we've already accomplished) is just one of countless real-world applications for SN33's Structured Data pipeline. We're building a decentralized Scale AI, offering a full suite of Structured Data commodities—from text metadata tagging (available today) to fully customizable queries for company-specific data annotation use cases and image metadata tagging coming soon 👀. Thanks for all the feedback! It has been invaluable so keep bringing it to us! 🙏$TAO Openτensor Foundaτion 1 “ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks” shows “The zero-shot accuracy of ChatGPT exceeds that of crowd-workers by about 25 percentage points on average [...] Moreover, the per-annotation cost of ChatGPT is less than $0.003—about thirty times cheaper than MTurk”

Studies have shown ChatGPT outperforms human annotators for Structured Data by about 25% and costs 30x less. 1 In just 2 months, miners on SN33 running ChatGPT without optimization can’t survive. Today we announce SN33 is now ReadyAI to fully align with our mission 👇 SN33 is building a more performant and significantly cheaper alternative to Scale AI Today structured data is performed primarily by human annotation services like Amazon’s Mechanical Turk and Scale AI It is now more important than ever for every business and individual to make their data AI Ready. However, taking unstructured data and making it Structured Data using today’s tools is extremely costly. SN33 revolutionizes this process, unlocking immense opportunities for commercialization. We lay out the vision for it in this detailed blog post: Validators TODAY can monetize access to this structured data pipeline independently, but we’re streamlining this process, launching a frontend soon that any validator can opt into to provide bandwidth. We've received great feedback from the community, recognizing that what we're building goes far beyond Conversational AI. Building the world's largest annotated conversational dataset (which we've already accomplished) is just one of countless real-world applications for SN33's Structured Data pipeline. We're building a decentralized Scale AI, offering a full suite of Structured Data commodities—from text metadata tagging (available today) to fully customizable queries for company-specific data annotation use cases and image metadata tagging coming soon 👀. Thanks for all the feedback! It has been invaluable so keep bringing it to us! 🙏$TAO Openτensor Foundaτion 1 “ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks” shows “The zero-shot accuracy of ChatGPT exceeds that of crowd-workers by about 25 percentage points on average [...] Moreover, the per-annotation cost of ChatGPT is less than $0.003—about thirty times cheaper than MTurk”

David Fields

13,639 Aufrufe • vor 2 Jahren

Andrej Karpathy just broke the entire premise of modern AI: "Agents aren't magic. They're distillation at scale." 99.99% of your LLM's capacity is wasted on garbage data it never needed. Small model + right tools + closed loop = terrifying capability. In a 16-minute conversation, Karpathy reveals the full reasoning stack. Worth more than any $500 AI course you've seen this year.

Andrej Karpathy just broke the entire premise of modern AI: "Agents aren't magic. They're distillation at scale." 99.99% of your LLM's capacity is wasted on garbage data it never needed. Small model + right tools + closed loop = terrifying capability. In a 16-minute conversation, Karpathy reveals the full reasoning stack. Worth more than any $500 AI course you've seen this year.

Morty

671,231 Aufrufe • vor 1 Monat

McKinsey says companies will spend $7 trillion on AI data centers by 2030. Most traders don’t realize only 20% of this money goes to computer chips everyone talks about. The other 80% flows to companies you've never heard of. Here's where the real money is going:

McKinsey says companies will spend $7 trillion on AI data centers by 2030. Most traders don’t realize only 20% of this money goes to computer chips everyone talks about. The other 80% flows to companies you've never heard of. Here's where the real money is going:

Felix Prehn 🐶

89,263 Aufrufe • vor 9 Monaten

ELON: THE FUTURE OF AI IS REAL-TIME VIDEO COMPREHENSION AND GENERATION Elon said most human-AI interaction will soon happen through real-time video, both in understanding and creating it. He explained that while text carries higher information density, video already dominates the internet in both data generation and compute demand: “Most interaction is going to be real-time video with AI, real-time video comprehension and real-time video generation. That’s going to be most of the load, and that’s how it is for most of the internet right now. Most of the internet is video. Text is a pretty small percentage, but it tends to be higher value or more densely compressed information. If you look at the most bits generated and compute spent, it’s certainly going to be video.” Source: Nikhil Kamath

ELON: THE FUTURE OF AI IS REAL-TIME VIDEO COMPREHENSION AND GENERATION Elon said most human-AI interaction will soon happen through real-time video, both in understanding and creating it. He explained that while text carries higher information density, video already dominates the internet in both data generation and compute demand: “Most interaction is going to be real-time video with AI, real-time video comprehension and real-time video generation. That’s going to be most of the load, and that’s how it is for most of the internet right now. Most of the internet is video. Text is a pretty small percentage, but it tends to be higher value or more densely compressed information. If you look at the most bits generated and compute spent, it’s certainly going to be video.” Source: Nikhil Kamath

Mario Nawfal

15,670 Aufrufe • vor 8 Monaten

Standard Intelligence's devansh responds to roon's tweet that "text is the universal interface," and explains why their new foundation model is trained on video: "At some point in the arbitrarily long future, if we only use text models, we could force most things to be text. But I think there are just a lot of things that are much more native when done from a computer-use [perspective]." "GUIs are designed for humans to use. We have this massive long tail of things on the internet that are entirely undoable by LLMs." "For example, when I do ML engineering most of my time is spent doing the grunt work of engineering. It's a lot of looking at graphs, analyzing, and comparing loss curves. You can do this in text, but it's a much larger pain than doing it in the native interface." "There's a reason humans don't interact with a computer purely through text, it would kind of suck."

Standard Intelligence's devansh responds to roon's tweet that "text is the universal interface," and explains why their new foundation model is trained on video: "At some point in the arbitrarily long future, if we only use text models, we could force most things to be text. But I think there are just a lot of things that are much more native when done from a computer-use [perspective]." "GUIs are designed for humans to use. We have this massive long tail of things on the internet that are entirely undoable by LLMs." "For example, when I do ML engineering most of my time is spent doing the grunt work of engineering. It's a lot of looking at graphs, analyzing, and comparing loss curves. You can do this in text, but it's a much larger pain than doing it in the native interface." "There's a reason humans don't interact with a computer purely through text, it would kind of suck."

TBPN

64,434 Aufrufe • vor 5 Monaten

We have data in abundance now. The real value isn't within the RAW Data, but is this data validated and verified? More value in data refinement. We have a solution for this which is validated by 6 years of research and development with the Department of Defense Now securing and validating commercial data from partners like Common Crawl and Panasonic

We have data in abundance now. The real value isn't within the RAW Data, but is this data validated and verified? More value in data refinement. We have a solution for this which is validated by 6 years of research and development with the Department of Defense Now securing and validating commercial data from partners like Common Crawl and Panasonic

Constellation²

10,559 Aufrufe • vor 1 Jahr

Announcing CREAO 2.0: Create your AI to work. How can a one-person team achieve the scale of 100? Meet the automation powerhouse you’ve been waiting for: Massive Execution: Automate Youtube, video editing, & Discord tickets. Hard-code your logic into tools for massive, 100% reliable output. Data Hub: Actions are captured as structured assets. Trace, analyze, and evolve your workflows into even more powerful Apps. Asset Accumulation: Every execution compounds data value, turning daily tasks into permanent digital assets. Create your AI to work. Why stay manual when you can automate? Create your growth engine today:

Announcing CREAO 2.0: Create your AI to work. How can a one-person team achieve the scale of 100? Meet the automation powerhouse you’ve been waiting for: Massive Execution: Automate Youtube, video editing, & Discord tickets. Hard-code your logic into tools for massive, 100% reliable output. Data Hub: Actions are captured as structured assets. Trace, analyze, and evolve your workflows into even more powerful Apps. Asset Accumulation: Every execution compounds data value, turning daily tasks into permanent digital assets. Create your AI to work. Why stay manual when you can automate? Create your growth engine today:

Creao AI

3,098,194 Aufrufe • vor 6 Monaten

Database: Text property now supports dual links One of the most requested features in 0.20 is here — dual links in the Text property. You can now mention and reference other files not only in the title row, but directly inside the Text field. This gives you greater flexibility when organizing and connecting your documents.

Database: Text property now supports dual links One of the most requested features in 0.20 is here — dual links in the Text property. You can now mention and reference other files not only in the title row, but directly inside the Text field. This gives you greater flexibility when organizing and connecting your documents.

Wax AI

48,478 Aufrufe • vor 5 Monaten

I wish it existed when I was doing PhD. It’d have saved me hours in literature reviews. Here is the FASTEST way to get a COMPLETE overview of any research field. 1. Go to 2. Type your research topic in one sentence 3. Review the structured plan Noah builds 4. Tweak or approve the structured plan 4. Watch it run: ✦ Database searches ✦ Clinical trial analysis, ✦ Web + medical literature deep dives ✦ And full verification 5. In 10 minutes, get a comprehensive, structured report with accurate in-text citations What you get: → A structured research plan you control before execution → Searches across PubMed, clinical trial registries, FDA, NIH, and more → Clinical data analyzed and cross-verified automatically → A full field overview, competitive landscape, drug pipelines, key findings → In-text citations from trusted sources, no hallucinations Try Noah AI today for FREE:

I wish it existed when I was doing PhD. It’d have saved me hours in literature reviews. Here is the FASTEST way to get a COMPLETE overview of any research field. 1. Go to 2. Type your research topic in one sentence 3. Review the structured plan Noah builds 4. Tweak or approve the structured plan 4. Watch it run: ✦ Database searches ✦ Clinical trial analysis, ✦ Web + medical literature deep dives ✦ And full verification 5. In 10 minutes, get a comprehensive, structured report with accurate in-text citations What you get: → A structured research plan you control before execution → Searches across PubMed, clinical trial registries, FDA, NIH, and more → Clinical data analyzed and cross-verified automatically → A full field overview, competitive landscape, drug pipelines, key findings → In-text citations from trusted sources, no hallucinations Try Noah AI today for FREE:

Faheem Ullah

11,980 Aufrufe • vor 1 Monat

VEO 3 + JSON prompting is pretty wild 🤯 These AG1 product videos were created entirely with AI. And it's all about the prompt. This JSON prompting technique will take any generic VEO3 prompt.. And turn it into surgical-precision video generation with brand consistency. Perfect for creative strategists, growth marketers & ad agencies. But instead of manually writing paragraph prompts and hoping for good outputs... Just use structured JSON prompts and get brand-ready videos with way higher coherence. The best part? Your prompt precision goes through the roof -> organized by camera angles, brand elements, lighting specs, & scene transitions. Here's what JSON prompting gives you: → structured data instead of paragraph descriptions → precise creative direction for VEO 3 → consistent brand-ready video outputs → way higher prompt coherence → eliminates the creative lottery problem Now you've got predictable video generation instead of random outputs. This isn't perfect yet — but in 6 months when brand videos need this precision? You'll be ahead of everyone. Want the full JSON prompt templates? Comment "JSON" + follow and I'll send it over (must be following so I can DM)

Mike Futia

252,552 Aufrufe • vor 1 Jahr

Indie devs, it's #WishlistWednesday! Show me your games below :) And remember, you are literally bringing worlds, characters, and mechanics into existence out of thin air. Most people only consume art, but you’re out here creating it. Never lose sight of how cool that is! ❤️

Indie devs, it's #WishlistWednesday! Show me your games below :) And remember, you are literally bringing worlds, characters, and mechanics into existence out of thin air. Most people only consume art, but you’re out here creating it. Never lose sight of how cool that is! ❤️

Indie Game Joe

58,176 Aufrufe • vor 6 Tagen

"There's a good chance that by the end of the year, people aren't using IDEs anymore." — Boris Cherny (Anthropic) Yes. The IDE is shrinking into a debugging and review tool for most devs most of the time. And the code host...who cares? Everything is changing, there is no moat.

"There's a good chance that by the end of the year, people aren't using IDEs anymore." — Boris Cherny (Anthropic) Yes. The IDE is shrinking into a debugging and review tool for most devs most of the time. And the code host...who cares? Everything is changing, there is no moat.

Quinn Slack

183,688 Aufrufe • vor 1 Jahr

The original habitant of Lagos are not Yoruba but the Awori 😂 This is a statement from an illiterate Ibo lady who doesn’t understand how the Yoruba Ethnicity is structured. Do you see why you should never fall for physical beauty?

The original habitant of Lagos are not Yoruba but the Awori 😂 This is a statement from an illiterate Ibo lady who doesn’t understand how the Yoruba Ethnicity is structured. Do you see why you should never fall for physical beauty?

𝗔𝗱𝗲́𝘀𝗶́𝗻𝗮̀ 🇳🇬

22,664 Aufrufe • vor 2 Monaten

FRIEDBERG: VIDEO DATA WILL POWER THE NEXT GENERATION OF AI Friedberg broke down the scale shift coming to artificial intelligence, arguing that text based models like GPT are just the beginning, and that the real revolution will come from video-trained systems: “The internet and all these LLMs are language models trained on text from the internet, around 50 billion words total, maybe one to five terabytes of data in their training sets. But if you look at the video data out there, there are hundreds of billions of hours, much of it on YouTube. By some estimates, there’s a thousand exabytes of video data on the internet, about a billion times more than text data. I think we just saw that play out with the new video model that launched yesterday. Google has all this YouTube data, whether or not they’re using it to train, I don’t know. I’ve heard from insiders they’re not allowed to yet and would have to redo the terms of service.” Source: AIFinInsights david friedberg

FRIEDBERG: VIDEO DATA WILL POWER THE NEXT GENERATION OF AI Friedberg broke down the scale shift coming to artificial intelligence, arguing that text based models like GPT are just the beginning, and that the real revolution will come from video-trained systems: “The internet and all these LLMs are language models trained on text from the internet, around 50 billion words total, maybe one to five terabytes of data in their training sets. But if you look at the video data out there, there are hundreds of billions of hours, much of it on YouTube. By some estimates, there’s a thousand exabytes of video data on the internet, about a billion times more than text data. I think we just saw that play out with the new video model that launched yesterday. Google has all this YouTube data, whether or not they’re using it to train, I don’t know. I’ve heard from insiders they’re not allowed to yet and would have to redo the terms of service.” Source: AIFinInsights david friedberg

Mario Nawfal

15,855 Aufrufe • vor 8 Monaten