codrutalugoj

HarmBench

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

AgentBench

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

MLAgentBench

reflexion

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

langchain

🦜🔗 Build context-aware reasoning applications

rome

Locating and editing factual associations in GPT (NeurIPS 2022)

communitynotes

Documentation and source code powering Twitter's Community Notes

ARENA_2.0

Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.

RLAlgorithms

Reinforcement learning algorithms, produced mostly or entirely from scratch.

evals

courses

This repository is a curated collection of links to various courses and resources about Artificial Intelligence (AI)

ML-Papers-of-the-Week

🔥Highlighting the top ML papers every week.

babyagi

TransformerLens

A library for mechanistic interpretability of GPT-style language models

uvadlc_notebooks

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023

manim

Animation engine for explanatory math videos

varibad

Implementation of VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning - Zintgraf et al. (ICLR 2020)

hyperx