Name: Evan Hubinger
Type: User
Company: Anthropic
Bio: Alignment Stress-Testing Team Lead @anthropics. Previously: @machine-intelligence, @openai, @google, @Yelp, @ripple.
Twitter: EvanHub
Location: San Francisco, California
Blog: https://www.alignmentforum.org/users/evhub
Evan Hubinger's Projects
PCGen - Open Source character generator for role-playing games
Harvey Mudd Physics 24a Problem Sets
A point-free implementation of a one-layer transformer in Coconut.
Calculate Pokemon speed tiers.
A framework for managing and maintaining multi-language pre-commit hooks.
Some out-of-the-box hooks for pre-commit
Run Prisoner's Dilemma competitions in Python.
Prisoner's Dilemma Competition
Resolution theorem proving for predicate logic in pure Python.
PyPy compiled to JavaScript
Python static type and rule checker
A python library for loading and reading configuration
An open-source Python implementation using JIT techniques.
Python 3 and Cython language bundles for Sublime Text and TextMate
An implementation of the Language Server Protocol for Python
Microsoft Language Server for Python
Library for building powerful interactive command lines in Python
PyWavelets - Discrete Wavelet Transform in Python
Interactive convnet features visualization for Keras
Rabbit is a modern, functional programming language built on top of Python.
An example of how to hook into Rabbit to create your own custom RabbitLang development environment.
Rainbow: Combining Improvements in Deep Reinforcement Learning
A markdown parser for docutils
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
Minimal and Clean Reinforcement Learning Examples
The source for my post "An exploration of relaxed adversarial training for inner alignment."
Handles basic build management for ripple development.