Pinned Loading

1. experiments experiments Public

   Python

2. dotfiles dotfiles Public

   Emacs Lisp

3. RylanSchaeffer/AstraFellowship-When-Do-VLM-Image-Jailbreaks-Transfer RylanSchaeffer/AstraFellowship-When-Do-VLM-Image-Jailbreaks-Transfer Public

   Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models

   Python 37 4

4. ucl-dark/llm_debate ucl-dark/llm_debate Public

   Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"

   Python 134 27

5. understanding-search/maze-transformer understanding-search/maze-transformer Public

   This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.

   Jupyter Notebook 35 7

6. omnibuser omnibuser Public

   Ruby 23 3