Evan Hubinger

Head of Alignment Stress-Testing at Anthropic

Starred Projects (124)

bloom by safety-research

LLM behavior evaluation system for uncovering model biases and tendencies

transitive-bullshit:

omarsar:

t3dotgg:

Created 7 months ago

Updated 1 week ago

petri by safety-research

Parallel exploration tool for risky interactions

gakonst:

Created 5 months ago

Updated 4 days ago

agentic-misalignment by anthropic-experimental

Framework for studying agentic misalignment in LLMs

omarsar:

simonw:

Created 7 months ago

Updated 7 months ago

workers-oauth-provider by cloudflare

OAuth 2.1 provider framework for Cloudflare Workers

kentcdodds:

transitive-bullshit:

Created 10 months ago

Updated 2 weeks ago

goose by block

Open-source AI agent for automating complex engineering tasks

ebursztein:

t3dotgg:

hsbt:

bryanhelmig:

Created 1 year ago

Updated 2 days ago

UI-TARS-desktop by bytedance

GUI agent app for computer control via natural language

hugs:

ekzhu:

hiyouga:

gregpr07:

Created 1 year ago

Updated 1 week ago

claude-code by anthropics

Agentic coding assistant for your terminal

bcherny:

alexey-milovidov:

chiphuyen:

gregpr07:

Created 11 months ago

Updated 2 days ago

entropix by xjdr-alt

Research project for entropy-based context-aware sampling & parallel CoT decoding

geohot:

vincentweisser:

snowzurfer:

bratseth:

Created 1 year ago

Updated 1 year ago

OpenHands by OpenHands

AI platform for software development agents

truell20:

pgarbacki:

khou22:

yiranwu0:

Created 1 year ago

Updated 1 day ago

mindcraft by mindcraft-bots

LLM agent for Minecraft

jspahrsummers:

binarybana:

jmorganca:

thomwolf:

Created 2 years ago

Updated 1 week ago

claude-engineer by Doriandarko

AI assistant for software development using Claude 3.5

jrk:

joewalnes:

doriandarko:

dguido:

Created 1 year ago

Updated 1 year ago

sparse_autoencoder by openai

Sparse autoencoder for GPT2-small activation analysis

transitive-bullshit:

vincentweisser:

Created 1 year ago

Updated 1 year ago

aider by Aider-AI

AI pair programming in your terminal

bcherny:

nat:

ekzhu:

hugs:

Created 2 years ago

Updated 1 week ago

inspect_ai by UKGovernmentBEIS

Framework for large language model evaluations

JohannesHa:

pgarbacki:

simonw:

eugeneyan:

Created 2 years ago

Updated 3 days ago

devika by stitionai

Agentic AI software engineer for high-level instruction to code generation

sxyu:

taranjeet:

gregpr07:

vincentweisser:

Created 1 year ago

Updated 4 months ago

simple-evals by openai

Lightweight library for evaluating language models

hammer:

patrickvonplaten:

simonw:

zhyncs:

Created 1 year ago

Updated 6 months ago

auto-code-rover by AutoCodeRoverSG

Autonomous software engineer for program improvement

dguido:

kelvich:

transitive-bullshit:

didierrlopes:

Created 1 year ago

Updated 9 months ago

llm-claude-3 by simonw

LLM plugin for interacting with the Claude 3 family of models

Created 1 year ago

Updated 11 months ago

claude-cookbooks by anthropics

Code & guides for building with Claude

parano:

osanseviero:

transitive-bullshit:

omarsar:

Created 2 years ago

Updated 1 day ago

transformer-debugger by openai

Tool for language model behavior investigation

aangelopoulos:

chiphuyen:

transitive-bullshit:

swyxio:

Created 1 year ago

Updated 1 year ago

dictionary_learning by saprmarks

Sparse autoencoder research code for neural network activations

Created 2 years ago

Updated 5 months ago

anthropic-sdk-python by anthropics

Python SDK for Anthropic's REST API

wolffiex:

samuelcolvin:

simonw:

philschmid:

Created 3 years ago

Updated 1 day ago

FastChat by lm-sys

Open platform for training, serving, and evaluating LLM-based chatbots

zjasper666:

aangelopoulos:

osanseviero:

natolambert:

Created 2 years ago

Updated 7 months ago

llm-attacks by llm-attacks

Attack framework for aligned LLMs, based on a research paper

ebursztein:

chiphuyen:

jph00:

hiyouga:

Created 2 years ago

Updated 1 year ago

langchain by langchain-ai

Framework for building LLM-powered applications

karpathy:

MagMueller:

gregpr07:

willingc:

Created 3 years ago

Updated 1 day ago

rl by pytorch

PyTorch library for reinforcement learning research

Jiayi-Pan:

natolambert:

Created 4 years ago

Updated 2 days ago

llm_multiagent_debate by composable-models

ICML 2024 research paper on multiagent debate improving LLM factuality

AntonOsika:

Created 2 years ago

Updated 9 months ago

developer by smol-ai

Agent for embedding a developer in your app

vanpelt:

chiphuyen:

shyamal-anadkat:

mchiang0610:

Created 2 years ago

Updated 1 year ago

AutoGPT by Significant-Gravitas

AI agent platform for building, deploying, and running autonomous workflows

lilianweng:

chiphuyen:

julien-c:

deshraj:

Created 2 years ago

Updated 1 day ago

gisting by jayelm

Research paper implementation for prompt compression via learned "gist" tokens

winglian:

Created 2 years ago

Updated 11 months ago

evals by openai

Framework for evaluating LLMs and LLM systems, plus benchmark registry

aangelopoulos:

chiphuyen:

agola11:

taranjeet:

Created 3 years ago

Updated 2 months ago

TaskMatrix by chenfei-wu

Visual ChatGPT connects LLMs to visual foundation models

chiphuyen:

taranjeet:

parano:

hiyouga:

Created 2 years ago

Updated 2 years ago

llama by meta-llama

Inference code for Llama 2 models (deprecated)

froystig:

xiezhq-hermann:

fabhed:

borzunov:

Created 2 years ago

Updated 1 year ago

llm-strategy by BlackHC

SDK for connecting Python to LLMs via typed functions

osanseviero:

Created 3 years ago

Updated 11 months ago

evals by anthropics

Model-written datasets for evaluating language model behaviors

vincentweisser:

transitive-bullshit:

ethanjperez:

Created 3 years ago

Updated 1 year ago

pythia by EleutherAI

LLM suite for interpretability, learning dynamics, ethics, and transparency research

hammer:

osanseviero:

calvinfo:

vincentweisser:

Created 4 years ago

Updated 2 months ago

OpenELM by CarperAI

OpenELM: evolutionary search with language models in code and natural language

vincentweisser:

transitive-bullshit:

hammer:

Created 3 years ago

Updated 2 years ago

minGPT by karpathy

Minimal PyTorch re-implementation for GPT training and inference

aravindsrinivas:

nat:

geohot:

lilianweng:

Created 5 years ago

Updated 1 year ago

TransformerLens by TransformerLensOrg

Library for mechanistic interpretability research on GPT-style language models

chiphuyen:

neelnanda-io:

Created 3 years ago

Updated 5 days ago

ice by oughtinc

LM program debugger and trace visualizer

transitive-bullshit:

agola11:

jordn:

omarsar:

Created 3 years ago

Updated 3 weeks ago

jaxtyping by patrick-kidger

Typing library for array shapes/dtypes

geohot:

patrickvonplaten:

ekzhang:

lucidrains:

Created 3 years ago

Updated 3 days ago

prize by inverse-scaling

Prize for tasks where larger language models perform worse

osanseviero:

vincentweisser:

huybery:

ethanjperez:

Created 3 years ago

Updated 2 years ago

metaseq by facebookresearch

Codebase for large-scale transformer model development and deployment

chiphuyen:

gakonst:

xiezhq-hermann:

Ying1123:

Created 3 years ago

Updated 1 year ago

rome by kmeng01

Model editing research paper for GPT-2 and GPT-J

hiyouga:

shizhediao:

stellaathena:

Created 4 years ago

Updated 1 year ago

lucent by greentfrapp

PyTorch adaptation of the Lucid feature visualization library

Created 5 years ago

Updated 10 months ago

TruthfulQA by sylinrl

Benchmark dataset for evaluating truthfulness of language models

winglian:

hammer:

collin-burns:

Created 4 years ago

Updated 1 year ago

loom by socketteer

Tree-based writing interface for human-AI collaboration

willccbb:

bryanhelmig:

JohannesHa:

vincentweisser:

Created 5 years ago

Updated 1 year ago

guided-diffusion by openai

Image synthesis codebase for diffusion models

aravindsrinivas:

JustinLin610:

rromb:

patrickvonplaten:

Created 4 years ago

Updated 1 year ago

gpt-neox by EleutherAI

Framework for training large-scale autoregressive language models

hammer:

stas00:

gakonst:

transitive-bullshit:

Created 5 years ago

Updated 1 month ago

mesh-transformer-jax by kingoflolz

JAX library for model-parallel transformers

gakonst:

parano:

nirga:

vincentweisser:

Created 4 years ago

Updated 3 years ago

bert by google-research

TensorFlow code and pre-trained models for BERT

aravindsrinivas:

pgarbacki:

jn2clark:

lewtun:

Created 7 years ago

Updated 1 year ago

best-of-ml-python by lukasmasuch

Curated list of Python ML libraries, ranked by quality score

Jiayi-Pan:

vnivargi:

tunguz:

omarsar:

Created 5 years ago

Updated 5 days ago

DALLE-pytorch by lucidrains

PyTorch implementation of DALL-E, OpenAI's text-to-image transformer

omarsar:

luiscape:

bfirsh:

chenlin9:

Created 5 years ago

Updated 1 year ago

DeBERTa by microsoft

BERT enhancement via disentangled attention, enhanced mask decoder

huybery:

hammer:

omarsar:

parasj:

Created 5 years ago

Updated 2 years ago

CLIP by openai

Image-text matching model for zero-shot prediction

aravindsrinivas:

transitive-bullshit:

Edward-Sun:

mholt:

Created 5 years ago

Updated 1 year ago

awful-ai by daviddao

Curated list of scary AI usages to raise awareness

swyxio:

jthandy:

eugeneyan:

ankane:

Created 7 years ago

Updated 11 months ago

gpt-3 by openai

Research paper on large language model few-shot learning

aravindsrinivas:

shizhediao:

Jiayi-Pan:

kentcdodds:

Created 5 years ago

Updated 5 years ago

pytorch-lightning by Lightning-AI

Deep learning framework for pretraining, finetuning, and deploying AI models

albertfgu:

soldni:

omarsar:

zhangce:

Created 6 years ago

Updated 4 days ago

transformers by huggingface

ML library for pretrained model inference and training

clmnt:

lilianweng:

karpathy:

tjbck:

Created 7 years ago

Updated 1 day ago

DeepSpeed by deepspeedai

Deep learning optimization library for distributed training and inference

aravindsrinivas:

ValentaTomas:

winglian:

stas00:

Created 6 years ago

Updated 1 day ago

procgen by openai

Procedurally-generated Gym environments for RL generalization research

ogabrielluiz:

Created 6 years ago

Updated 2 years ago

safety-starter-agents by openai

RL algorithms for safe exploration research paper

vincentweisser:

Created 6 years ago

Updated 2 years ago

random-network-distillation by openai

RL research paper code

aravindsrinivas:

millionintegrals:

junxiaosong:

Created 7 years ago

Updated 5 years ago

numpyro by pyro-ppl

Probabilistic programming library using JAX for GPU/TPU/CPU

omarsar:

froystig:

yang-song:

hammer:

Created 7 years ago

Updated 3 days ago

vime by openai

RL research paper code

aravindsrinivas:

pathak22:

jachiam:

nottombrown:

Created 9 years ago

Updated 7 years ago

numpy-ml by ddbourgin

ML algorithms implemented in NumPy

aravindsrinivas:

thinkall:

parano:

hammer:

Created 6 years ago

Updated 2 years ago

InfoGAN by openai

Research paper implementation for interpretable representation learning via InfoGAN

aravindsrinivas:

ericjang:

mattjj:

lukemetz:

Created 9 years ago

Updated 4 years ago

gym-http-api by openai

HTTP API for OpenAI Gym environments

deshraj:

Created 9 years ago

Updated 2 years ago

generating-reviews-discovering-sentiment by openai

Language model code for generating reviews and discovering sentiment

aravindsrinivas:

shyamal-anadkat:

vincentweisser:

luiscape:

Created 8 years ago

Updated 2 years ago

improved-gan by openai

GAN training code for research paper replication

aravindsrinivas:

lilianweng:

bcherny:

vincentweisser:

Created 9 years ago

Updated 7 years ago

xlnet by zihangdai

Language model research paper using generalized autoregressive pretraining

ankane:

stas00:

shizhediao:

forresti:

Created 6 years ago

Updated 2 years ago

gym-soccer by openai

Multi-agent environment for continuous-space soccer tasks

ogabrielluiz:

Created 9 years ago

Updated 2 years ago

coinrun by openai

RL research environment and training script

aravindsrinivas:

Created 7 years ago

Updated 2 years ago

multiagent-particle-envs by openai

Multi-agent environment for actor-critic research

aravindsrinivas:

apsdehal:

mattjj:

AntonOsika:

Created 8 years ago

Updated 1 year ago

pixel-cnn by openai

TensorFlow implementation for PixelCNN++ research paper

aravindsrinivas:

jinze1994:

omarsar:

chuanli11:

Created 9 years ago

Updated 6 years ago

neural-mmo by openai

Massively multiagent game environment for training and evaluating intelligent agents

jiamings:

millionintegrals:

apsdehal:

rwightman:

Created 7 years ago

Updated 2 years ago

atari-py by openai

Deprecated Python package for Atari 2600 environment access

aravindsrinivas:

simonw:

pathak22:

Created 9 years ago

Updated 2 years ago

roboschool by openai

Deprecated robot simulation software integrated with OpenAI Gym

aravindsrinivas:

truell20:

bcherny:

vincentweisser:

Created 8 years ago

Updated 2 years ago

mujoco-py by openai

Python bindings for MuJoCo physics engine

lilianweng:

aravindsrinivas:

ogabrielluiz:

jinze1994:

Created 9 years ago

Updated 2 years ago

deep-rl by pemami4911

Deep reinforcement learning algorithms collection

jn2clark:

Created 10 years ago

Updated 6 years ago

bert_language_understanding by brightmart

Pre-training toolkit for language understanding tasks

Created 7 years ago

Updated 7 years ago

retro by openai

RL environment for classic video games

aravindsrinivas:

deshraj:

apsdehal:

wojzaremba:

Created 8 years ago

Updated 1 year ago

Rainbow by Kaixhin

Deep reinforcement learning research paper implementation

millionintegrals:

jwyang:

iamtrask:

jekbradbury:

Created 8 years ago

Updated 4 years ago

gpt-2 by openai

Code for research paper "Language Models are Unsupervised Multitask Learners"

aravindsrinivas:

simonw:

0hq:

shyamal-anadkat:

Created 7 years ago

Updated 1 year ago

clip-as-service by jina-ai

Scalable CLIP embedding service for images and text

lilianweng:

jn2clark:

parano:

ankane:

Created 7 years ago

Updated 2 years ago

examples by pytorch

PyTorch examples for diverse AI tasks

lilianweng:

hammer:

tjbck:

ari-holtzman:

Created 9 years ago

Updated 4 months ago

blocksparse by openai

TensorFlow ops/GPU kernels for block-sparse matrix multiplication and convolution

aravindsrinivas:

gakonst:

shizhediao:

jamesr66a:

Created 8 years ago

Updated 2 years ago

Made-With-ML by GokuMohandas

ML course for production-grade applications

pcmoritz:

robinjhuang:

ogabrielluiz:

chiphuyen:

Created 7 years ago

Updated 1 year ago

ray by ray-project

AI compute engine for scaling Python and AI applications

beyang:

hsbt:

gregpr07:

hiyouga:

Created 9 years ago

Updated 1 day ago

Deep-reinforcement-learning-with-pytorch by sweetice

PyTorch library for deep reinforcement learning algorithms

shizhediao:

lllyasviel:

Created 7 years ago

Updated 2 years ago

awesome-deeplearning-resources by endymecy

Deep learning research paper and code repository

shizhediao:

apsdehal:

sb2nov:

Created 9 years ago

Updated 1 month ago

awesome-cbir-papers by willard-yuan

Papers for content-based image retrieval (CBIR) in academia/industry

transitive-bullshit:

huybery:

Created 10 years ago

Updated 2 years ago

keras-resources by fchollet

Keras resources directory for deep learning tutorials and code

aravindsrinivas:

ebursztein:

Created 9 years ago

Updated 1 year ago

trpo by pat-coady

Reinforcement learning implementation with OpenAI Gym

deshraj:

junxiaosong:

Created 8 years ago

Updated 5 years ago

awesome-nlp by keon

Curated list of NLP resources

bcherny:

ankane:

lysandrejik:

chiphuyen:

Created 10 years ago

Updated 1 day ago

awesome-deep-learning-music by ybayle

Curated list of deep learning articles applied to music

cvalenzuela:

chuanli11:

jongwook:

Created 8 years ago

Updated 2 years ago

Reinforcement-learning-with-tensorflow by MorvanZhou

RL tutorials for basic to advanced algorithms

jinze1994:

Created 8 years ago

Updated 1 year ago

AgentNet by yandexdataschool

Deep reinforcement learning library

junxiaosong:

AntonOsika:

jachiam:

Created 10 years ago

Updated 8 years ago

tensorflow-reinforce by yukezhu

TensorFlow implementations of reinforcement learning models

nottombrown:

codekansas:

AntonOsika:

Created 9 years ago

Updated 8 years ago

awesome-rl by aikorea

Curated list of reinforcement learning resources

spartee:

carlosejimenez:

junxiaosong:

ericjang:

Created 10 years ago

Updated 2 years ago

gym-minecraft by tambetm

Gym environment for AI experimentation/research in Minecraft

jiamings:

pathak22:

Created 9 years ago

Updated 4 years ago

ganhacks by soumith

GAN training tips and tricks

aravindsrinivas:

lilianweng:

ebursztein:

stefanv:

Created 9 years ago

Updated 4 years ago

reinforcement-learning by dennybritz

RL algorithms implementation for education

lilianweng:

ogabrielluiz:

thomwolf:

jinze1994:

Created 9 years ago

Updated 2 years ago

pytorch-tutorial by yunjey

PyTorch tutorial for deep learning researchers

tjbck:

bryanhelmig:

stas00:

haotian-liu:

Created 9 years ago

Updated 2 years ago

tqdm by tqdm

Progress bar for Python and CLI tools

bcherny:

geohot:

hugs:

parano:

Created 10 years ago

Updated 8 months ago

spaCy by explosion

NLP library for production applications

aravindsrinivas:

fchollet:

nirga:

jn2clark:

Created 11 years ago

Updated 2 months ago

rl-teacher by nottombrown

RL from human preferences via a webapp for feedback collection

aravindsrinivas:

janleike:

jiamings:

8enmann:

Created 8 years ago

Updated 3 years ago

reinforcement-learning by rlcode

Reinforcement learning examples for algorithm exploration

fchollet:

junxiaosong:

AntonOsika:

jiamings:

Created 9 years ago

Updated 2 years ago

baselines by openai

RL algorithm implementations for research

aravindsrinivas:

lilianweng:

JohannesHa:

jspahrsummers:

Created 8 years ago

Updated 1 year ago

tensor2tensor by tensorflow

Deprecated library for deep learning models/datasets, successor to Trax

lilianweng:

aravindsrinivas:

eiso:

JohannesHa:

Created 8 years ago

Updated 2 years ago

CNTK by microsoft

Deep-learning toolkit for neural networks as directed computational graphs

bcherny:

tiangolo:

luiscape:

parano:

Created 10 years ago

Updated 2 years ago

keras-rl by keras-rl

Deep reinforcement learning algorithms in Python, Keras-integrated

aravindsrinivas:

fchollet:

lysandrejik:

vincentweisser:

Created 9 years ago

Updated 2 years ago

universe by openai

Deprecated platform for measuring/training AI across diverse applications

Jiayi-Pan:

codekansas:

junxiaosong:

steve8708:

Created 9 years ago

Updated 7 years ago

pyo3 by PyO3

Rust bindings for Python, enabling native extension modules

chiphuyen:

didierrlopes:

charliermarsh:

hammer:

Created 8 years ago

Updated 4 days ago

neon by NervanaSystems

Deep learning framework (discontinued)

fchollet:

parano:

trishume:

hanlint:

Created 11 years ago

Updated 5 years ago

tsfresh by blue-yonder

Python package for time series feature extraction

bcherny:

hammer:

rodrigosnader:

tunguz:

Created 9 years ago

Updated 2 months ago

TopDeepLearning by aymericdamien

Deep learning project list, ranked by stars

aravindsrinivas:

parasj:

jasonwei20:

luiscape:

Created 9 years ago

Updated 1 year ago

awesome-bigdata by oxnr

Curated list of big data frameworks, resources, and tools

eddyxu:

developit:

vnivargi:

Created 11 years ago

Updated 2 months ago

pattern by clips

Python web mining module

hammer:

stas00:

AntonOsika:

generall:

Created 14 years ago

Updated 1 year ago

rllab by rll

Framework for reinforcement learning algorithm development and evaluation

aravindsrinivas:

gdb:

apsdehal:

parano:

Created 9 years ago

Updated 2 years ago

gym by openai

RL toolkit for reinforcement learning algorithm development

aravindsrinivas:

fchollet:

bcherny:

ValentaTomas:

Created 9 years ago

Updated 1 year ago

cleverhans by cleverhans-lab

Adversarial example library for benchmarking ML model robustness

lilianweng:

huybery:

generall:

colah:

Created 9 years ago

Updated 1 year ago

brick by jtdaugherty

Haskell TUI toolkit

Created 10 years ago

Updated 2 weeks ago

tensorflow by tensorflow

Open-source ML framework

norvig:

aravindsrinivas:

karpathy:

bcherny:

Created 10 years ago

Updated 1 day ago

Feedback? Help us improve.