Nosia – Privacy-focused AI to run models on your own data and device
What happens when you wait months after the official release of ChatGPT, with all the media buzz, before you actually try it for the first time? What happens when your first question to ChatGPT is about its carbon footprint, including Scope 3 emissions, and whether OpenAI complies with the Paris Agreement? What happens when, back in 2013, you almost left tech to become a beekeeper, but then returned to the field driven by passion and a vision for doing things differently? What happens when you believe in extending the life of terminals and servers, recycling, and reusing hardware, instead of…
What it does
In the maker’s words, at launch
What happens when you wait months after the official release of ChatGPT, with all the media buzz, before you actually try it for the first time? What happens when your first question to ChatGPT is about its carbon footprint, including Scope 3 emissions, and whether OpenAI complies with the Paris Agreement? What happens when, back in 2013, you almost left tech to become a beekeeper, but then returned to the field driven by passion and a vision for doing things differently? What happens when you believe in extending the life of terminals and servers, recycling, and reusing hardware, instead of succumbing to programmed obsolescence or deleting old emails? What happens when you believe in the power of the French and European tech ecosystem to provide digital solutions that respect GDPR and uphold core values? What happens when you stand for data sovereignty, empowering organizations to protect their data and act independently? What happens when you champion open-source and collective intelligence as key drivers of innovation? What happens when you work with code, systems, networks, and cybersecurity, and approach your work like a craftsman, building something meaningful? Introducing Nosia – a platform that allows you to run an AI model directly on your own data and device, from small models (SLM) to large models (LLM). It's designed to be easy to install and use, empowering you to take control of your AI needs while respecting privacy, sustainability, and autonomy.
Does the same job
all alternatives →
- CPChatGPT-powered dystopia simulator2023 · future.attejuvonen.fi · ▲195
OP here. This comment contains SPOILERS so try the dystopia simulator first before reading further! I built "WeChatGPT+" in December on top of GPT-3. It was pretty surreal when OpenAI released an actual product named "ChatGPT Plus" a few months after that. Then the Microsoft partnership was announced, Bing AI was released, and marketing materials were leaked indicating that Bing AI would start including advertisements within the chat responses. Reality imitates fiction, I guess. Today - literally a few hours ago - OpenAI announced public ChatGPT API with 10% the cost of GPT-3. I immediately…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, November 2024
the whole month →
- IB
I wasn't quite sure if this qualified as "Show HN" given you can't really download it and try it out. However, dang said[0]: > If it's hardware or something that's not so easy to try out over the internet, find a different way to show how it actually works—a video, for example, or a detailed post with photos. Hopefully I did that? Additionally, I've put code and a detailed guide for the netboot computer management setup on GitHub: https://github.com/kentonv/lanparty Anyway, if this shouldn't have been Show HN, I apologize! [0]…
Dev tools · 2024 · lanparty.house
