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.

Stop reading the text !!! Have a graphic dialogue with OpenAI’s #GPT4 with #Graphologue. It turns GPT4-generated text into interactive node-link diagrams in real-time. New Human-Computer Interaction #HCI research makes #AI easier to use. More at

Haijun Xia

4,045 subscribers

335,518 Aufrufe • vor 3 Jahren •via X (Twitter)

Wissenschaft & Technologie #GPT4 #Graphologue #HCI #AI

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von Neethan Wu

Neethan Wuvor 3 Jahren

This interactive node link makes much more sense and would be really helpful when it comes to some serious knowledge reading. Is this one open sourced? Or any SDK that I could tryout Graphologue?

Profilbild von Haijun Xia

Haijun Xiavor 3 Jahren

@neethanverse We are working hard on making this available to the world.

Profilbild von Goran Majić

Goran Majićvor 3 Jahren

What about mind maps? I'm searching for something between @theoasisAI (just talk and AI gives you the perfect written text) and Grapholouge: A neural AI engine that opens/structures my neural brain thoughts. Showing me maybe where the borders of my thoughts are and how it can go on with other options. @mattmireles

Profilbild von George Stoitzev

George Stoitzevvor 3 Jahren

When can we use this?

Profilbild von Haijun Xia

Haijun Xiavor 3 Jahren

@Georgeblue94 Working hard on it!

Profilbild von jian

jianvor 3 Jahren

This is super cool!! Are the generated responses always structured semantically like root -> children? What happens if we merge similar roots/children together and create a knowledge graph? And how does it support long responses/documents? Are there any special processing needed?

Profilbild von Daniel Buschek

Daniel Buschekvor 3 Jahren

Looks great! From the short video I can already spot so many interaction details you must have thought about, wow! 👏 Is there a paper/preprint?

Profilbild von Haijun Xia

Haijun Xiavor 3 Jahren

It’s on the way :)

Profilbild von Kevin L

Kevin Lvor 3 Jahren

Awesome work done here! Even though some processes in our brains function in parallel, our human thinking process is largely constrained to be sequential. Projects like these are really important for keeping track of LLM outputs and enhancing our understanding.

Profilbild von Haijun Xia

Haijun Xiavor 3 Jahren

@Braincorpceo indeed, the roots of these designs are in the understanding of the general human cognitive processes, as well as embracing the flexibility and dynamics one may desire for their context

Ähnliche Videos

What if #ChatGPT were 3D? Structure #GPT4's responses in 3D with #Sensecape to better understand large amounts of text. New Human-Computer Interaction #HCI research makes #AI easier to use. More at

What if #ChatGPT were 3D? Structure #GPT4's responses in 3D with #Sensecape to better understand large amounts of text. New Human-Computer Interaction #HCI research makes #AI easier to use. More at

Haijun Xia

79,533 Aufrufe • vor 3 Jahren

Introducing GPT-4o, our new model which can reason across text, audio, and video in real time. It's extremely versatile, fun to play with, and is a step towards a much more natural form of human-computer interaction (and even human-computer-computer interaction):

Introducing GPT-4o, our new model which can reason across text, audio, and video in real time. It's extremely versatile, fun to play with, and is a step towards a much more natural form of human-computer interaction (and even human-computer-computer interaction):

Greg Brockman

4,361,590 Aufrufe • vor 2 Jahren

I made another film with Ai. This time I used #runwayml ‘s text to video Ai #gen2 . Each shot was prompted. Voices generated with #elevenlabs I wrote the story based on a tweet #gpt4 wrote: “I just had a dream that I was an AI and woke up in a lab. What does it mean?” #aicinema

I made another film with Ai. This time I used #runwayml ‘s text to video Ai #gen2 . Each shot was prompted. Voices generated with #elevenlabs I wrote the story based on a tweet #gpt4 wrote: “I just had a dream that I was an AI and woke up in a lab. What does it mean?” #aicinema

Jon Finger

270,297 Aufrufe • vor 3 Jahren

Cleaned up the previous post's text box into something more usable. The text wraps around to fit into the dialogue box, which you can resize with the corner controls. You can download it from the link here, it's free.

Cleaned up the previous post's text box into something more usable. The text wraps around to fit into the dialogue box, which you can resize with the corner controls. You can download it from the link here, it's free.

Miracle

15,005 Aufrufe • vor 1 Jahr

Manetho is digitizing the museum experience with AI. Using computer vision and NLP, it translates hieroglyphs in real time and turns artifacts into interactive learning tools. Built on Huawei Cloud, ModelArts, and MindSpore, it supports deeper access to Egyptian history.

Manetho is digitizing the museum experience with AI. Using computer vision and NLP, it translates hieroglyphs in real time and turns artifacts into interactive learning tools. Built on Huawei Cloud, ModelArts, and MindSpore, it supports deeper access to Egyptian history.

Huawei

1,552,492 Aufrufe • vor 2 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

BREAKING: ChatGPT GPT-4o was just announce by OpenAI. It improves on vision, audio and text. The ease of use is incredibly enhanced. It makes interaction with the GPT much more natural, especially with voice. GPT-4o reasons across voice, text and vision. GPT-4 wil be available to everyone.

BREAKING: ChatGPT GPT-4o was just announce by OpenAI. It improves on vision, audio and text. The ease of use is incredibly enhanced. It makes interaction with the GPT much more natural, especially with voice. GPT-4o reasons across voice, text and vision. GPT-4 wil be available to everyone.

Ed Krassenstein

21,605 Aufrufe • vor 2 Jahren

Introducing Interactive Build. Build faster. Build smarter. Interactive Build lets you collaborate directly with Alchemist AI via text or voice, powered by OpenAI’s real-time APIs. No need to craft the perfect prompt from scratch, just start talking. Describe your idea, and Alchemist AI will guide you with intelligent, dynamic questions, transforming your vision into a structured, optimized prompt ready for generation. Whether you’re starting fresh or refining an existing project, Interactive Build streamlines the process, taking you from concept to execution faster, with less effort and no guesswork. One conversation. One creation. All in real time.

Introducing Interactive Build. Build faster. Build smarter. Interactive Build lets you collaborate directly with Alchemist AI via text or voice, powered by OpenAI’s real-time APIs. No need to craft the perfect prompt from scratch, just start talking. Describe your idea, and Alchemist AI will guide you with intelligent, dynamic questions, transforming your vision into a structured, optimized prompt ready for generation. Whether you’re starting fresh or refining an existing project, Interactive Build streamlines the process, taking you from concept to execution faster, with less effort and no guesswork. One conversation. One creation. All in real time.

ALCHEMIST AI 🔮

19,789 Aufrufe • vor 1 Jahr

Vidu S1, the World’s Most Advanced Model for Real-Time AI Interaction Vidu S1 introduces a new era of real-time interactive video. Voice-Driven Character Control: Go beyond voice-driven lip sync with real-time behavior generation. Characters understand, react, and respond naturally. Unlimited Real-Time Generation: Experience seamless real-time video generation with unlimited interaction duration. 540P at 25 FPS, built for live interaction: Generate video in real time at 540P / 25 FPS, with support for up to 42 FPS for even smoother experiences. Create Custom Characters from Images & Voices: Customize both appearance and voice. Bring humans, anime characters, pets, and more to life with personalized AI characters. Use code VIDUS1 to get started for free.

Vidu S1, the World’s Most Advanced Model for Real-Time AI Interaction Vidu S1 introduces a new era of real-time interactive video. Voice-Driven Character Control: Go beyond voice-driven lip sync with real-time behavior generation. Characters understand, react, and respond naturally. Unlimited Real-Time Generation: Experience seamless real-time video generation with unlimited interaction duration. 540P at 25 FPS, built for live interaction: Generate video in real time at 540P / 25 FPS, with support for up to 42 FPS for even smoother experiences. Create Custom Characters from Images & Voices: Customize both appearance and voice. Bring humans, anime characters, pets, and more to life with personalized AI characters. Use code VIDUS1 to get started for free.

Vidu AI

1,533,747 Aufrufe • vor 1 Monat

Users define the experience. Bubble Code brings the AI host live. Through xBubble, you can build and deploy an interactive avatar livestream room with real-time video, audience chat, live responses, and session controls. Not a prerecorded digital human, a ready-to-use AI livestream product built for real interaction.

DAPPOS

101,488 Aufrufe • vor 1 Monat

NotebookLM just went from smart… to unstoppable. And nobody is talking about how big this update really is. Google just gave Notebook LM the ability to read your photos → handwritten notes, textbook pages, graphs, screenshots. Here’s how to use it: → Upload any image (notes, diagrams, whiteboards). → Notebook LM runs OCR and turns it into clean text. → Ask it anything about the image. → Use Deep Research to pull in verified web sources. → Build a complete research hub in minutes. This is the first time your messy notes become a searchable knowledge base. Save this video, you’ll need it. Full guide is inside AI Money Lab. DM me for the link. 💬

NotebookLM just went from smart… to unstoppable. And nobody is talking about how big this update really is. Google just gave Notebook LM the ability to read your photos → handwritten notes, textbook pages, graphs, screenshots. Here’s how to use it: → Upload any image (notes, diagrams, whiteboards). → Notebook LM runs OCR and turns it into clean text. → Ask it anything about the image. → Use Deep Research to pull in verified web sources. → Build a complete research hub in minutes. This is the first time your messy notes become a searchable knowledge base. Save this video, you’ll need it. Full guide is inside AI Money Lab. DM me for the link. 💬

Julian Goldie SEO

13,157 Aufrufe • vor 9 Monaten

wtf.. this is mindblowing.. GoogleDeepMind just dropped Genie 3 you can generate interactive 3D world with text, navigate with keys and.. interact in real time.. AI is crazy 10 examples: 1. navigate to a car and open the door.. omg

wtf.. this is mindblowing.. GoogleDeepMind just dropped Genie 3 you can generate interactive 3D world with text, navigate with keys and.. interact in real time.. AI is crazy 10 examples: 1. navigate to a car and open the door.. omg

el.cine

1,450,621 Aufrufe • vor 1 Jahr

Very, very, very impressed by Google I/O today. Highlights: #Veo, AI video generator (1080p, more than a minute), working with donald (Childish Gambino) Gemini 1.5 Pro (GPT4-level model) with 2 million tokens Google Search now has an agent built in to do complex searches Text to Music AI Sandbox, working with Wyclef Jean Imagen 3, DALLE3/4 level model Astra Links to everything in 🧵

Very, very, very impressed by Google I/O today. Highlights: #Veo, AI video generator (1080p, more than a minute), working with donald (Childish Gambino) Gemini 1.5 Pro (GPT4-level model) with 2 million tokens Google Search now has an agent built in to do complex searches Text to Music AI Sandbox, working with Wyclef Jean Imagen 3, DALLE3/4 level model Astra Links to everything in 🧵

andrew gao

301,740 Aufrufe • vor 2 Jahren

wow.. this AI is crazy you can now use Google Gemini 2.0 image editor on FLORA and its much more advanced you can edit image with simple text and turn it into commercial video directly it's free to use for a limited time now, link in comment 10 examples:

wow.. this AI is crazy you can now use Google Gemini 2.0 image editor on FLORA and its much more advanced you can edit image with simple text and turn it into commercial video directly it's free to use for a limited time now, link in comment 10 examples:

el.cine

1,371,909 Aufrufe • vor 1 Jahr

Playing around with KREA AI real-time video ✨ Stream from your webcam and it diffuses in real-time based on your video + a text prompt. I turned my Philz cup into a magic potion!

Playing around with KREA AI real-time video ✨ Stream from your webcam and it diffuses in real-time based on your video + a text prompt. I turned my Philz cup into a magic potion!

Justine Moore

28,574 Aufrufe • vor 11 Monaten

As a researcher, this used to take me 3–4 hours. - Reading papers - Copying text into ChatGPT - Switching between tabs - Trying to compare findings Then I came across Tabbit: With Tabbit, it takes 20 minutes. Here’s how → Open your research papers directly in your browser → No more copy-pasting into ChatGPT or Claude → Just chat with the paper right there It doesn’t stop here.

As a researcher, this used to take me 3–4 hours. - Reading papers - Copying text into ChatGPT - Switching between tabs - Trying to compare findings Then I came across Tabbit: With Tabbit, it takes 20 minutes. Here’s how → Open your research papers directly in your browser → No more copy-pasting into ChatGPT or Claude → Just chat with the paper right there It doesn’t stop here.

Faheem Ullah

160,364 Aufrufe • vor 4 Monaten

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Stability AI

976,610 Aufrufe • vor 2 Jahren

➡️ Sometimes, the best way to capture information is with a clear diagram! Our latest AI tool, AI Diagrams, takes simple text and turns it into the visual of your choice. From there, easily save the result to your Evernote account, or copy/download it directly from the web. Check it out below👇and try the tool for yourself:

➡️ Sometimes, the best way to capture information is with a clear diagram! Our latest AI tool, AI Diagrams, takes simple text and turns it into the visual of your choice. From there, easily save the result to your Evernote account, or copy/download it directly from the web. Check it out below👇and try the tool for yourself:

Evernote

16,827 Aufrufe • vor 1 Jahr

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