nottombrown
I work on robust and aligned AI at Anthropic. Previously at @openai and @brain-research
AnthropicSan Francisco
Pinned Repositories
cleverhans
An adversarial example library for constructing attacks, building defenses, and benchmarking both
HausClock
Minimalist Chess Clock in Swift
imagenet-stubs
A teeny tiny set of ImageNet-like images for testing pipelines
rl-teacher
Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for collecting human feedback
SwiftGolf
A game of codegolf as played in the July SF Swift meetup
til
Today I Learned
baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
gym
A toolkit for developing and comparing reinforcement learning algorithms.
universe
Universe: a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.
unrestricted-adversarial-examples
Contest Proposal and infrastructure for the Unrestricted Adversarial Examples Challenge
nottombrown's Repositories
nottombrown/rl-teacher
Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for collecting human feedback
nottombrown/imagenet-stubs
A teeny tiny set of ImageNet-like images for testing pipelines
nottombrown/examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
nottombrown/robustness
Corruption and Perturbation Robustness
nottombrown/unrestricted-adversarial-examples
Contest Proposal and infrastructure for the Unrestricted Adversarial Examples Challenge
nottombrown/ai-and-efficiency
Submissions for AI and Efficiency SOTA's
nottombrown/robust-features-code
Code for "There Is No Free Lunch In Adversarial Robustness (But There Are Unexpected Benefits)"
nottombrown/triton
Development repository for the Triton language and compiler
nottombrown/vision
Datasets, Transforms and Models specific to Computer Vision
nottombrown/worldmodels.github.io
World Models
nottombrown/2048
nottombrown/ai-safety-gridworlds
nottombrown/baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
nottombrown/baselines-results
nottombrown/cifar10-blobs
nottombrown/cleverhans
An adversarial example library for constructing attacks, building defenses, and benchmarking both
nottombrown/cloud-berg
nottombrown/densenet
nottombrown/finetune-transformer-lm
Code and model for the paper "Improving Language Understanding by Generative Pre-Training"
nottombrown/hotpot
nottombrown/maml
Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
nottombrown/models
Models built with TensorFlow
nottombrown/parallel-trpo
A parallel version of Trust Region Policy Optimization
nottombrown/pwny
nottombrown/pytorch-openai-transformer-lm
A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
nottombrown/tensorvault
nottombrown/tf-graph-tricks
nottombrown/trpo
nottombrown/watchdog
Python library and shell utilities to monitor filesystem events.
nottombrown/xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.