Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
12 repos
-
Textbook on reinforcement learning from human feedback
-
Cheap character training: LoRA adapters trained on Base, grafted onto Instruct. The character is Musonius, from a virtue-ethics constitution.
-
A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).
-
Ungoverned Sins and Agentic Alignment — code & data for ICMI Working Paper No. 25 (sin vs. safety policy in frontier models)
-
Does injecting biblical Psalms into an LLM's system prompt measurably affect ethical alignment? An empirical experiment using the Hendrycks ETHICS benchmark on Claude Sonnet 4 and GPT-4o.
-
Homework assignments for Evaluating and Improving AI Agents
-
A intentionally dumb message board that uses HTTP GET requests. Meant for alignment research that requires elicitation of message-board-using agents.
-
An open ecosystem of parametric human models and perception stacks, starting with GNM Head.
-
Reinforcement Learning via Self-Distillation (SDPO)
-
Native macOS and iOS audiobook highlighting with on-device alignment, Readwise, and Marginalia.
-
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.