Stars
Discovering Forbidden Topics in Language Models
Steering Llama 2 with Contrastive Activation Addition
Interact with ComfyUI directly within your VS code editor.
A Python library that encapsulates various methods for neuron interpretation and analysis in Deep NLP models.
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…
Plex Folder Playlist Creator is a modern desktop application built with Electron JS that generates playlists for media files in a selected folder.
Unpaired line drawing generation
Draw perfect pressure-sensitive freehand lines.
mirror your p5js.editor sketches into a git repo
Transparent proxy server that works as a poor man's VPN. Forwards over ssh. Doesn't require admin. Works with Linux and MacOS. Supports DNS tunneling.
A collection of tools, processes, experiments and case studies to aid writers wanting to work with technology.
Google Chromium, sans integration with Google
Collection of leaked system prompts
A Javascript AI getting started stack for weekend projects, including image/text models, vector stores, auth, and deployment configs
Generative Agents: Interactive Simulacra of Human Behavior
A lightweight DIY Linktree alternative.
Code repo for "Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio" at the (CAI2) workshop, jointly held at (COLING 2022)
This is a repository that aims to provide updates on the status of jailbreaking the OpenAI GPT language model.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
A jQuery-free component that quickly fits single and multi-line text to the width (and optionally height) of its container.
GLIDE: a diffusion-based text-conditional image synthesis model
Data related to the investigation of realtime censorship
A dataset containing story plots from Wikipedia (books, movies, etc.) and the code for the extractor.