someone just open-sourced their own neuro-sama. and it might be better than the original.
it's called airi.
a fully autonomous ai companion that talks to you in real time, plays minecraft and factorio with you, chats on discord and telegram, and has a live2d/vrm avatar body. runs entirely on your machine.
→ real-time voice conversations, speech recognition
→ animated avatar with auto-blink, eye tracking, idle animations
→ persistent memory across sessions
→ local inference via webgpu, no api calls needed
supports 30+ llm providers, openai, claude, gemini, deepseek, ollama, groq, mistral, xai, local models. swap the brain with a config change. runs on native cuda and apple metal for real gpu acceleration.
17.5k stars. 101 contributors. 46 releases.
100% free. open source.
💫DID YOU KNOW💫
that if you move a mouse cursor fast enough, you can get persistence of vision and, say...
*run a game of Pong inside your mouse's firmware*
🕹️🕹️🕹️🕹️🕹️🕹️🕹️🕹️🕹️
Join the Taiwan Ubuntu LoCo team's Ubuntu 24.04 Release Party on June 1, 2024! We'll discuss the key updates of the Nobel Numbat release. Come, ask questions and let's have a great discussion. #UbuntuReleaseParty https://t.co/SLnnp0Xxb1
Use silent #SMS messages to track LTE users’ locations
An attacker sends silent SMS messages with a defined pattern and analyze LTE traffic to verify the victim location.
All you need is just: SDR + SIM cards + LTESniffer software
https://t.co/fFfiBmmGgs
Segment Anything in High Quality
paper page: https://t.co/acknyb7GAy
propose HQ-SAM, equipping SAM with the ability to accurately segment any object, while maintaining SAM's original promptable design, efficiency, and zero-shot generalizability. Our careful design reuses and preserves the pre-trained model weights of SAM, while only introducing minimal additional parameters and computation. We design a learnable High-Quality Output Token, which is injected into SAM's mask decoder and is responsible for predicting the high-quality mask. Instead of only applying it on mask-decoder features, we first fuse them with early and final ViT features for improved mask details. To train our introduced learnable parameters, we compose a dataset of 44K fine-grained masks from several sources. HQ-SAM is only trained on the introduced detaset of 44k masks, which takes only 4 hours on 8 GPUs. We show the efficacy of HQ-SAM in a suite of 9 diverse segmentation datasets across different downstream tasks, where 7 out of them are evaluated in a zero-shot transfer protocol.
Watching llama.cpp do 40 tok/s inference of the 7B model on my M2 Max, with 0% CPU usage, and using all 38 GPU cores.
Congratulations @ggerganov ! This is a triumph.
https://t.co/C6mn7jkMLb