Hyperspace: More Nodes Is All You Need

Talk transcript

1. 0:00

   [upbeat music] Hello, everybody. Uh, my name is Nicolas Schlaepfer.

2. 0:16

   I'm an AI engineer. I think I'm at the right place. Um, today I'm gonna be pronouncing, uh, a new product we've been working on at Hyperspace. Um, a little bit about us.

3. 0:28

   Uh, we are a decentralized AI network. Uh, we have no GPUs. Um, we're building a community who takes, uh, the resources from their personal computer and contributes, uh, to our decentralized network.

4. 0:44

   Um, we have a product currently out called AI OS. Um, you can download it for Windows and Mac. It uses llama.cpp and does inference. So technically you can download it, get inference from somebody in Belgium, and you can have a chat experience like that.

5. 1:00

   So we're hoping to... Oh, actually, sorry. Um, we really believe in, uh, diverse models. Uh, we think, uh, not having, um, just one big closed source model is the answer for the best AI experience.

6. 1:17

   Um, having a mixture of a bunch of great experts will provide the best AI experience.

7. 1:24

   Um, so that gets us to our self-titled product, Hyperspace, which will be built on our network. Um, this is a really interesting product. It's a mix of prompt engineering, um, visual, uh, React Flow, uh, Python execution, and, uh, RAG-like, uh, web browsing.

8. 1:46

   So for the first thing with this product, we wanted to build a, uh, fine-tuned model that outputted agentic planning experiences. So you'd put in a query, you get in a DAG, or you get out a DAG in a JSON format, and this is a, uh, a methodical plan from that query.

9. 2:06

   Um, we also wanted to have a primitive of having a in-house web scraping experience for LLMs. So we're using Puppeteer and Beautiful Soup to scrape websites, convert that, uh, HTML into, uh, a Markdown, something easier to read for LLMs to digest.

10. 2:28

    Um, kind of the product we're gonna talk about is, uh, we have a node editor and a terminal, and this is gonna be a power tool for the power users.

11. 2:37

    Um, this node editor will allow you to change each node in the React Flow to, uh, fit your needs, and this is coming from the DAG org- or DAG orchestration model we have.

12. 2:49

    Um, here's a little video demo of, uh, our product. I recorded it yesterday in the hotel, so I'm sorry for the audio, and here we go. [gentle music]

13. 3:08

    Welcome to a very early look at Hyperspace. Let's begin with a sample query.

14. 3:20

    Once you submit your query, you're brought into our node editor view, where each node is streamed in from our DAG orchestration model, HyperEngine V3.

15. 3:31

    We want to emphasize that the user's still in full control. They can edit the title, task description, and expected output.

16. 3:39

    They also have the freedom to add as many nodes as they like.

17. 3:46

    Let's execute. Now that our outputs are done, we can talk a little bit about the outputs. Each output is coming from each node, and each node is creating a query based on that task.

18. 4:06

    It's combining the overall goal, the local goal, and whatever's happened in the previous node.

19. 4:13

    We're using a reasoning model and a summarization model. For reasoning, we're using Qwen2 Instruct, and then for summarization, we're using Llama 370B. This helps provide a diverse set of synthesized answers.

20. 4:30

    For the outputs that do have Python, we can go ahead and run them and see them in our terminal.

21. 4:39

    Terminal will automatically open it up with the output.

22. 4:43

    We want to provide the groundwork for agentic behavior in the future by providing these core primitives.

23. 4:52

    Over here on our right, we have our virtual file system that changes our directory.

24. 4:58

    We're trying to build out all the primitives to what an agent would need: memory, Python execution, planning, and code generation.

25. 5:08

    Thank you so much for watching. We're very excited to get this out in the coming weeks. [upbeat music] [audience applauding]

26. 5:18

    Um, happy to announce that'll be available later this week via waitlist, so go ahead and pay attention to our Twitter, Hyperspace AI. All right. Thank you. That's my time. [upbeat music]