Pinned Repositories
EscalAItion
Repo for the paper on Escalation Risks of AI systems
CS-348C-HW
Homework for CS 348C at Stanford University.
LVRC-Unreal
Implementing the character controller, interaction system, and hand presence from Half-Life: Alyx as a plugin in Unreal Engine.
Minitorch-Self-Study-Guide-SAIA
Minitorch Self-Study Guide (SAIA)
MLAB-Transformers-From-Scratch
Reimplementing transformers from scratch (from Redwood Research's Machine Learning for Alignment Bootcamp).
Rogue-Starfighter-VR
A VR game about piloting a starfighter from a galaxy far, far away.
Sundari-A-Procedural-Mandalorian-City
Procedurally building and animating the Mandalorian city of Sundari from Star Wars: The Clone Wars using Houdini.
Unadaptable-Foundation-Models
welfare-diplomacy
General-Sum variant of the game Diplomacy for evaluating AIs.
superhf
Open-source Human Feedback Library
mukobi's Repositories
mukobi/welfare-diplomacy
General-Sum variant of the game Diplomacy for evaluating AIs.
mukobi/MLAB-Transformers-From-Scratch
Reimplementing transformers from scratch (from Redwood Research's Machine Learning for Alignment Bootcamp).
mukobi/Minitorch-Self-Study-Guide-SAIA
Minitorch Self-Study Guide (SAIA)
mukobi/Unadaptable-Foundation-Models
mukobi/LVRC-Unreal
Implementing the character controller, interaction system, and hand presence from Half-Life: Alyx as a plugin in Unreal Engine.
mukobi/Portfolio-Generator
Generates my portfolio sites using Python, YAML, and Jinja2 and statically serves them over GitHub pages.
mukobi/Unsupervised-Concept-Based-Explanations-For-Sentiment-Analysis
Learning Unsupervised Concept-Based Explanations with Language Models for Sentiment Analysis.
mukobi/AI-Acumen-Resources
Additional figures and calculations for my AI strategy blog, https://aiacumen.substack.com
mukobi/attendee-search
Find EAG attendees with specific interests with semantic search
mukobi/CS-11SI-Teaching-Materials
See https://cs11si.stanford.edu/
mukobi/cs362
AI safety paper explorations for CS 362: Research in AI Alignment at Stanford.
mukobi/Film-Portfolio
mukobi/LLM-Multiplication-Tables
Evaluating GPT-3's 2-digit multiplication abilities for fun.
mukobi/lm-evaluation-harness
A framework for few-shot evaluation of language models.
mukobi/Minitorch-Module-0
Minitorch Module 0 (Fundamentals). Doing Minitorch again this summer.
mukobi/Minitorch-Module-1
Minitorch Module-1: Autodiff
mukobi/Minitorch-Module-2
Minitorch Module 2: Tensors
mukobi/Minitorch-Module-3
Minitorch Module 3: Efficiency
mukobi/mmlu_and_hhh_evals
Fork of Measuring Massive Multitask Language Understanding | ICLR 2021
mukobi/model-written-evals-continuation
mukobi/Module-0-OLD
Module 0 - Fundamentals
mukobi/Module-1-OLD
Module 1 - Autodifferentiation
mukobi/mukobi.github.io
An online portfolio for Gabriel Mukobi.
mukobi/My-Productivity-Workflow
Documenting my tools and techniques for being productive.
mukobi/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
mukobi/Photography-Portfolio
A photography portfolio by Gabriel Mukobi. If you enjoy these images, also consider viewing my 3D art and other portfolios.
mukobi/Pomodoro-Schedule-Notifier
Pomodoro timer synced to a fixed schedule that lives in the Windows notification area and notifies state with an icon and optionally sound.
mukobi/pozyx-clone
mukobi/Public-Scripts
My publicly shared scripts.
mukobi/sticksandstones
A website for the software development portfolio of Gabriel Mukobi