Lists (18)
Stars
AnkiDroid: Anki flashcards on Android. Your secret trick to achieve superhuman information retention.
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.
The Assistant Axis is a direction in activation space that captures how "Assistant-like" a model's behavior is. Models can drift away from the Assistant during conversations—sometimes toward bizarr…
You've probably been using Claude irresponsibly. Today, you can turn a new leaf.
Speedrunning LoRA fine-tuning: frozen task, frozen hardware, public wall-clock leaderboard. modded-nanogpt for fine-tuning.
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
Measuring how deeply LLMs adopt induced personas (Persona-Adoption Depth & Value Drift)
Keep your Mac awake only while AI coding agents are working
A toy Inspect implementation of the Bliss Attractor eval from Claude 4 System Card Welfare Assessment
Repository of "Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers" paper
The best open-source alternative to Superwhisper & Wispr Flow. Voice-to-text app for macOS with no subscription
Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)
Field Theory CLI for bookmarks, Library, commands, and agent workflows
A proof-of-concept eval testing whether models continue with (or mention) pre-filled malign behaviours.
Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs
Training LLMs to Report Their Learned Behaviors
A unified hub to create, simulate, and evaluate methods for patient/client simulation.
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
Official code for the paper: "Simple LLM Baselines are Competitive for Model Diffing"
This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix some of the annoying things you get from only using Claude cod…
A public-domain dataset of prompts and scenarios for evaluating compliance with the OpenAI Model Spec.