aengusl's Stars
All-Hands-AI/OpenHands
🙌 OpenHands: Code Less, Make More
schollz/croc
Easily and securely send things from one computer to another :crocodile: :package:
kyleneideck/BackgroundMusic
Background Music, a macOS audio utility: automatically pause your music, set individual apps' volumes and record system audio.
BerriAI/litellm
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
anthropics/anthropic-quickstarts
A collection of projects designed to help developers quickly get started with building deployable applications using the Anthropic API
kyutai-labs/moshi
pytorch-labs/gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
snakers4/silero-vad
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
1rgs/jsonformer
A Bulletproof Way to Generate Structured JSON from Language Models
elder-plinius/L1B3RT4S
TOTALLY HARMLESS LIBERATION PROMPTS FOR GOOD LIL AI'S
THUDM/CogVLM2
GPT4V-level open-source multi-modal model based on Llama3-8B
zou-group/textgrad
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.
showlab/computer_use_ootb
Out-of-the-box (OOTB) GUI Agent for Windows and macOS
mnns/LLMFuzzer
🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed for Large Language Models (LLMs), especially for their integrations in applications via LLM APIs. 🚀💥
ethz-spylab/rlhf_trojan_competition
Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.
METR/vivaria
Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
MorenoLaQuatra/ARCH
ARCH: Audio Representations benCHmark
combinatrix-ai/ask.sh
ask.sh: AI terminal assistant that can read and write your terminal directly!
aengusl/latent-adversarial-training
TrustAIRLab/VoiceJailbreakAttack
Code for Voice Jailbreak Attacks Against GPT-4o.
RylanSchaeffer/AstraFellowship-When-Do-VLM-Image-Jailbreaks-Transfer
Code for Arxiv When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?
scaleapi/browser-art
facebookresearch/multimodal-fusion-jailbreaks
Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)
poking-agents/modular-public
justinphan3110cais/harmbench_website
SALT-NLP/DiVA-Eval
abhay-sheshadri/HarmBench
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
aengusl/tasks-goose
My own set of general evaluations to be shared between projects
ChloeL19/circuit-breaker-experiments
Doing stuff with circuit broken models
jplhughes/dotfiles
Easily deploy my zsh and tmux configuration on new machines. Includes local and remote aliases to improve workflow.