正在加载视频...
视频加载失败
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
335,518 次观看 • 3 年前 •via X (Twitter)
10 条评论
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?
@neethanverse We are working hard on making this available to the world.
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
When can we use this?
@Georgeblue94 Working hard on it!
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?
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?
It’s on the way :)
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.
@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
![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."](https://image.24vids.com/tw-2026673713304007095/amplify_video_thumb/2026673583116951552/img/226ivXcDTOsUrDUD.jpg)