firstuserhere's Projects
experiments trying to elicit out of context learning when training a transformer on a simple task
Collection of google colaboratory notebooks for fast and easy experiments
An awesome curated list of resources dedicated to Mechanistic interpretability
a bunch of basic scripts hacked together but working and are maybe useful for me
ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications
Config files for my GitHub profile.
This is my website
The development repository for LessWrong2 and the EA Forum, based on Vulcan JS
Forking to add functionality for automated betting
Testing GPT-4 Vision on Advanced examination questions (2023) across physics, chemistry, and mathematics
Solve puzzles. Learn CUDA.
Critiques of the pre-print, suggestions for improvement, and counterfactual examples testing
Investigating the 4.39 problem from Concrete Open Problems
A Bulletproof Way to Generate Structured JSON from Language Models
The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.
Manifold Markets: A market for every question
Ongoing research training transformer models at scale
This is a repository and github pages website deployment for my work on the mechanistic analysis of out-of-context meta-learning in LLMs
Fork of a possible solution for testing
Basic mech interp analysis for some multimodal models
National Novel Generation Month, 2023 edition.