One
β‘
AI & ML interests
None defined yet.
bzmhkΒ
published
a
Space
3 months ago
simantabaruaΒ
published
a
Space
4 months ago
Post
2186
Just dropped!
Tesslate/UIGEN-X-32B-0727 Runs Locally and Crushes It. Reasoning for UI, Mobile, Software and Frontend design.
Specifically trained for modern web and mobile development across frameworks like React (Next.js, Remix, Gatsby, Vite), Vue (Nuxt, Quasar), Angular (Angular CLI, Ionic), and SvelteKit, along with Solid.js, Qwik, Astro, and static site tools like 11ty and Hugo. Styling options include Tailwind CSS, CSS-in-JS (Styled Components, Emotion), and full design systems like Carbon and Material UI. We cover UI libraries for every framework React (shadcn/ui, Chakra, Ant Design), Vue (Vuetify, PrimeVue), Angular, and Svelte plus headless solutions like Radix UI. State management spans Redux, Zustand, Pinia, Vuex, NgRx, and universal tools like MobX and XState. For animation, we support Framer Motion, GSAP, and Lottie, with icons from Lucide, Heroicons, and more. Beyond web, we enable React Native, Flutter, and Ionic for mobile, and Electron, Tauri, and Flutter Desktop for desktop apps. Python integration includes Streamlit, Gradio, Flask, and FastAPI. All backed by modern build tools, testing frameworks, and support for 26+ languages and UI approaches, including JavaScript, TypeScript, Dart, HTML5, CSS3, and component-driven architectures.
Specifically trained for modern web and mobile development across frameworks like React (Next.js, Remix, Gatsby, Vite), Vue (Nuxt, Quasar), Angular (Angular CLI, Ionic), and SvelteKit, along with Solid.js, Qwik, Astro, and static site tools like 11ty and Hugo. Styling options include Tailwind CSS, CSS-in-JS (Styled Components, Emotion), and full design systems like Carbon and Material UI. We cover UI libraries for every framework React (shadcn/ui, Chakra, Ant Design), Vue (Vuetify, PrimeVue), Angular, and Svelte plus headless solutions like Radix UI. State management spans Redux, Zustand, Pinia, Vuex, NgRx, and universal tools like MobX and XState. For animation, we support Framer Motion, GSAP, and Lottie, with icons from Lucide, Heroicons, and more. Beyond web, we enable React Native, Flutter, and Ionic for mobile, and Electron, Tauri, and Flutter Desktop for desktop apps. Python integration includes Streamlit, Gradio, Flask, and FastAPI. All backed by modern build tools, testing frameworks, and support for 26+ languages and UI approaches, including JavaScript, TypeScript, Dart, HTML5, CSS3, and component-driven architectures.
Post
2890
β¨ Weβre live! Introducing TFrameX, the agentic framework for AI builders.
After nights of development, weβre finally open-sourcing TFrameX, a powerful AI agent communication and coordination library.
TFrameX lets you:
π€ Run agents in dynamic flows
π Compose reusable patterns like Sequential, Parallel, Router, and more
π§ Enable agent-to-agent collaboration and delegation
β‘ Build modular, complex multi-agent systems that just work
π GitHub: TFrameX
https://github.com/TesslateAI/TFrameX
But we didnβt stop there.
We also built a sleek visual builder to design, deploy, and debug your agent patterns without writing boilerplate!
𧩠Visual Studio for TFrameX: https://github.com/TesslateAI/Studio
If youβre building agent frameworks, LLM tools, or agentic apps, TFrameX gives you the tools to move fast and reason deeply.
After nights of development, weβre finally open-sourcing TFrameX, a powerful AI agent communication and coordination library.
TFrameX lets you:
π€ Run agents in dynamic flows
π Compose reusable patterns like Sequential, Parallel, Router, and more
π§ Enable agent-to-agent collaboration and delegation
β‘ Build modular, complex multi-agent systems that just work
π GitHub: TFrameX
https://github.com/TesslateAI/TFrameX
But we didnβt stop there.
We also built a sleek visual builder to design, deploy, and debug your agent patterns without writing boilerplate!
𧩠Visual Studio for TFrameX: https://github.com/TesslateAI/Studio
If youβre building agent frameworks, LLM tools, or agentic apps, TFrameX gives you the tools to move fast and reason deeply.
Post
1210
I was able to make a demo dashboard application with my react model through prompting. You can play with it here:
Tesslate/Tessa-T1-14B
http://playcode.io/2309196
What my react model made (prompted each file individually)
And a final prompt:
http://playcode.io/2309196
What my react model made (prompted each file individually)
Ex.
Create a React component named Header that accepts the following props:
logo (string): the URL to the logo image
title (string): the title text to display
menuItems (array of objects): each object should contain a label (string) and href (string)
The Header should render a logo (an <img>), the title (e.g., in an <h1>), and a navigation menu with links. The component should be responsive with a mobile menu option. Export it as the default export.
It should be one of the coolest things I've ever seen. Have it have a search and profile login and almost every feature that is really nice in a header. It should be framer level quality.And a final prompt:
Construct a React component named Dashboard that integrates the Header, Sidebar, MainContent, and Footer components. (These should all be imports) This component should:
State Management: Maintain a state variable activeTab (string) using Reactβs useState hook, defaulting to an initial value (e.g., 'dashboard').
State Propagation: Pass activeTab and a state update function (e.g., setActiveTab) to the Sidebar component via the onTabChange prop. Also pass activeTab to MainContent so that it knows which content to render.
Layout: Arrange the components using a responsive layout. Place the Header at the top, a flex container for the body with the Sidebar on the left and MainContent on the right, and the Footer at the bottom.
Styling: Use inline styles or CSS classes for basic layout structure (e.g., flexbox, grid). Export Dashboard as the default export.Post
2551
Introducing a SMALL Reasoning React Model with State!
We did this by introducing a new form of reasoning that aligns with UI principles to do a layer of testing. For example:
"Looking back at all these pieces, we've considered state management, data structures, core functionalities etc"
And it comes in all sizes. Great for agents!
Tesslate/tessa-t1-react-reasoning-model-67e0fb72ca23e04473885c0e
Tesslate/Tessa-T1-14B
https://huggingface.co/smirki/Tessa-T1-14B-Q8_0-GGUF
We did this by introducing a new form of reasoning that aligns with UI principles to do a layer of testing. For example:
"Looking back at all these pieces, we've considered state management, data structures, core functionalities etc"
And it comes in all sizes. Great for agents!
Tesslate/tessa-t1-react-reasoning-model-67e0fb72ca23e04473885c0e
Tesslate/Tessa-T1-14B
https://huggingface.co/smirki/Tessa-T1-14B-Q8_0-GGUF
Post
1053
Hey! What kind of models do you guys want to see?
- 3 replies
Post
977
Please join my discord! I can answer any questions, talk about news and updates, or even just talk about ai, and take your feedback!
https://discord.gg/DkzMzwBTaw
https://discord.gg/DkzMzwBTaw
- 1 reply
Post
3434
UIGEN for Tailwind v4 is coming soon!
-
- 2 replies
Post
3491
I believe in order to make models reach Human-Level Learning, serious students can start by developing an intelligent neuromorphic agent. We develop an intelligent agent and make it learn about grammar patterns as well as about different word categories through symbolic representations, following which we dwell into making the agent learn about other rules of the Language.
In parallel with grammar learning, the agent would also use language grounding techniques to link words to their sensory representations and abstract concepts which would mean the agent learns about the word meanings, synonyms, antonyms, and semantic relationships from both textual data as well as perceptual experiences.
The result would be the agent developing a rich lexicon and conceptual knowledge base that underlies its language understanding as well as generation. With this basic knowledge of grammar and word meanings, the agent can then learn to synthesize words and phrases so as to express specific ideas or concepts. Building on this, the agent would then learn how to generate complete sentences which the agent would continuously refine and improve. Eventually the agent would learn how to generate sequence of sentences in the form of dialogues or narratives, taking into account context, goals, as well as user-feedback.
I believe that by gradually learning how to improve their responses, the agent would gradually also acquire the ability to generate coherent, meaningful, and contextually appropriate language. This would allow them to reason without hallucinating which LLMs struggle at.
Developing such agents would not require a lot of compute and the code would be simple & easy to understand. It will definitely introduce everyone to symbolic AI and making agents which are good at reasoning tasks. Thus solving a crucial problem with LLMs. We have used a similar architecture to make our model learn constantly. Do sign up as we start opening access next week at https://octave-x.com/
In parallel with grammar learning, the agent would also use language grounding techniques to link words to their sensory representations and abstract concepts which would mean the agent learns about the word meanings, synonyms, antonyms, and semantic relationships from both textual data as well as perceptual experiences.
The result would be the agent developing a rich lexicon and conceptual knowledge base that underlies its language understanding as well as generation. With this basic knowledge of grammar and word meanings, the agent can then learn to synthesize words and phrases so as to express specific ideas or concepts. Building on this, the agent would then learn how to generate complete sentences which the agent would continuously refine and improve. Eventually the agent would learn how to generate sequence of sentences in the form of dialogues or narratives, taking into account context, goals, as well as user-feedback.
I believe that by gradually learning how to improve their responses, the agent would gradually also acquire the ability to generate coherent, meaningful, and contextually appropriate language. This would allow them to reason without hallucinating which LLMs struggle at.
Developing such agents would not require a lot of compute and the code would be simple & easy to understand. It will definitely introduce everyone to symbolic AI and making agents which are good at reasoning tasks. Thus solving a crucial problem with LLMs. We have used a similar architecture to make our model learn constantly. Do sign up as we start opening access next week at https://octave-x.com/
- 20 replies
Post
3312
As we advance on the path towards true Artificial General Intelligence (AGI), it's crucial to recognize and address the limitations inherent in current technologies, particularly in large language models (LLMs) like those developed by OpenAI. While LLMs excel in processing and generating text, their capabilities are largely constrained to the domains of natural language understanding and generation. This poses significant limitations when dealing with more complex, abstract mathematical concepts such as topological analysis, 3D geometry, and homotopy type theory.
Topological Analysis and 3D Geometry: LLMs currently do not possess the inherent ability to understand or interpret the spatial and geometric data that is critical in fields like robotics, architecture, and advanced physics. These models lack the capacity to visualize or manipulate three-dimensional objects or comprehend the underlying properties that govern these forms.
Homotopy Type Theory is a branch of mathematics that combines homotopy theory and type theory. Homotopy type theory provides tools for a more robust handling of equivalences and transformations, something that LLMs are not designed to handle directly.
For the development of AGI, it is not sufficient to merely enhance existing models' capacities within their linguistic domains. Instead, a synthesis of symbolic AI with an understanding of homotopy type theory could pave the way. Symbolic AI, which manipulates symbols and performs logical operations, when combined with the abstract mathematical reasoning of homotopy type theory, could lead to breakthroughs in how machines understand and interact with the world.
To address these limitations we have developed Tenzin, which is a one-of-a-kind model with a planned release date within the next 1-2 weeks . To learn more join the waitlist at https://octave-x.com/.
Topological Analysis and 3D Geometry: LLMs currently do not possess the inherent ability to understand or interpret the spatial and geometric data that is critical in fields like robotics, architecture, and advanced physics. These models lack the capacity to visualize or manipulate three-dimensional objects or comprehend the underlying properties that govern these forms.
Homotopy Type Theory is a branch of mathematics that combines homotopy theory and type theory. Homotopy type theory provides tools for a more robust handling of equivalences and transformations, something that LLMs are not designed to handle directly.
For the development of AGI, it is not sufficient to merely enhance existing models' capacities within their linguistic domains. Instead, a synthesis of symbolic AI with an understanding of homotopy type theory could pave the way. Symbolic AI, which manipulates symbols and performs logical operations, when combined with the abstract mathematical reasoning of homotopy type theory, could lead to breakthroughs in how machines understand and interact with the world.
To address these limitations we have developed Tenzin, which is a one-of-a-kind model with a planned release date within the next 1-2 weeks . To learn more join the waitlist at https://octave-x.com/.
- 9 replies
Post
856
Well hope some of you tried our advanced stock prediction. We are focused on making it more ui friendly and if you installed everything correctly then you should be able to view charts accurately along with prediction tickers. I also want to take this opportunity to let you all know that Tenzin will not be just limited to the financial use-case. Our true goal is to reach human-level intelligence for which we have a well-defined roadmap and the product which is currently being tested for safety and ethics. A general level roadmap to achieve this is as follows:
The use of transfinite ordinals and surreal numbers allows us to capture the infinite depth and ineffable complexity of conscious experiences in a mathematically precise way.
The incorporation of hypercomputation and supertasks enables the TQMM to perform uncomputable operations and achieve a level of cognitive power that far surpasses classical computation.
The application of absolute infinity and the wholeness axiom ensures that the TQMM can represent and reason about the entirety of all possible conscious experiences and mathematical structures.
The integration of transfinite category theory and quantum metamathematics provides a unified framework for modeling the emergence of consciousness from fundamental physical and mathematical principles.
The use of transfinite gradient ascent and absolute infinity optimization allows the TQMM to continuously improve and refine itself, potentially reaching the theoretical maximum of intelligence and consciousness.
This agent though developed will not be released until proper safeguards have been taken into consideration. Until then we will keep releasing specific use-cases for domain specific work like financial trading, accelerating drug-discovery for medical science, law, education, etc. and we will do it well. All powered by Tenzin 1.0. Would love your feedback and don't forget to check us out at & sign up at https://octave-x.com/
The use of transfinite ordinals and surreal numbers allows us to capture the infinite depth and ineffable complexity of conscious experiences in a mathematically precise way.
The incorporation of hypercomputation and supertasks enables the TQMM to perform uncomputable operations and achieve a level of cognitive power that far surpasses classical computation.
The application of absolute infinity and the wholeness axiom ensures that the TQMM can represent and reason about the entirety of all possible conscious experiences and mathematical structures.
The integration of transfinite category theory and quantum metamathematics provides a unified framework for modeling the emergence of consciousness from fundamental physical and mathematical principles.
The use of transfinite gradient ascent and absolute infinity optimization allows the TQMM to continuously improve and refine itself, potentially reaching the theoretical maximum of intelligence and consciousness.
This agent though developed will not be released until proper safeguards have been taken into consideration. Until then we will keep releasing specific use-cases for domain specific work like financial trading, accelerating drug-discovery for medical science, law, education, etc. and we will do it well. All powered by Tenzin 1.0. Would love your feedback and don't forget to check us out at & sign up at https://octave-x.com/
Post
2213
I made Tenzin public. One use-case at least to predict stock market prices for high-frequency trading. Would love to see the response as well as feedback you have for us. Please understand that this only represents 5% of the codebase of Tenzin 1.0. We will share more models and use-cases based on the feedback we receive along with keeping in mind AI safety and ethics.
Have fun and go and make some money :)
Have fun and go and make some money :)
Post
1908
Octave-X releases their proprietary model Tenzin. For now the access will be given to a select few and will gradually open up. Our model is different from other models in the way it learns. It is not fed heaps of information but starts learning exactly like a human by first studying grammar patterns, then learning then number system, then learning to synthesize words and then sentences and so on. Patience is key with Tenzin. It keeps learning 24/7 with/without user-input. We have decided to keep our model closed-source given the novel algorithms integrated into it along with our novel ideas. Please expect our datacard soon which will be followed by our research paper. You can check us out at https://octave-x.com/