Name: Logan Kirkland
Type: User
Company: Azoth Corp
Bio: applied anthropologist of tech, space, & media, VR/ML/AI researcher & developer, coder, cyberneticist, semiotician, founder Azoth Corp, lead Mnemosyne Labs
Twitter: LericDax
Location: Sol System
Blog: www.LericDax.com
Logan Kirkland's Projects
Automatic gradient descent
Generative Agents Urban Simulation: Interactive Simulacra of Human Behavior
A Task-Driven Autonomous Agent System as an AI-powered solution that leverages LLMs, vector search, and the LangChain framework to efficiently complete, generate, and prioritize tasks using a wide range of different concepts.
ArcEyed is a Python application that detects and matches eyebrows in images.
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
An experimental open-source attempt to make GPT-4 fully autonomous.
Building a set of semantic kernel skills to act as a virtual developer team
Baize is an open-source chatbot trained with ChatGPT self-chatting data.
simple python tool with GUI to batch translate mp3 to wav
Bespoke Automata is a GUI and deployment pipline for making complex AI agents locally and offline
An experimental assemblage of agents.
Open source codebase powering the HuggingChat app
Converts multisamples from a source format (WAV, multisample, KMP, wavestate, NKI, SFZ, SoundFont 2) to a different destination format.
a simple game of cellular entropy
Mamba-Chat: A chat LLM based on the state-space model architecture 🐍
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
JARVIS, a system to connect LLMs with ML community
DNA foundation modeling from molecular to genome scale
A Python script with a GUI to automate the extraction of the last frame from a video.
A GPT-powered autonomous agent system
Example Discord bot written in Python that uses the completions API to have conversations with the `text-davinci-003` model, and the moderations API to filter the messages.
ImageBind One Embedding Space to Bind Them All
Instant neural graphics primitives: lightning fast NeRF and more
PyTorch code and models for V-JEPA self-supervised learning from video.
How might we mix OpenAI and Langchain and ElevenLabs to speak out responses to prompts using a body of knowledge encapsulated in PDFs?