Stars
Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.
🟣 LLMs interview questions and answers to help you prepare for your next machine learning and data science interview in 2026.
The Little Book of Reinforcement Learning
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.
100+ LLM interview questions with answers.
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
An active paper-reading skill that reconstructs author reasoning, explains methods mechanistically, stress-tests assumptions, and generates follow-up research ideas.
Open-source implementation of AlphaEvolve
Framework for evaluating and improving agents
AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ sc…
🧮 MathDial: A Dialog Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems, EMNLP Findings 2023
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
A curated collection of AI agent research papers released in 2026, covering agent engineering, memory, evaluation, workflows, and autonomous systems.
AI agents running research on single-GPU nanochat training automatically
Awesome Agent Skills collection list, papers, tools, projects, and resources
Search & disable undertrain tokens in Qwen3.6 and other BPE tokenizer models to improve its performance in corner case (or more) / 寻找并禁用Qwen3.6(及其它BPE分词器)的欠训练token以提高corner case下（也许不止）的能力
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
A dataset of LLM-generated chain-of-thought steps annotated with mistake location.
Machine Learning and Computer Vision Engineer - Technical Interview Questions
A curated catalogue of awesome agentic AI patterns
Hindsight: Agent Memory That Learns
repo for paper https://arxiv.org/abs/2504.13837
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering