Command & Conquer: Generals Remote Code Execution and Worm

Enterprise-grade Private Model-as-a-Service Platform

Nano vLLM

Bf-Tree is a modern read-write-optimized concurrent larger-than-memory range index in Rust from MS Research.

Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard. Track costs, debug prompts, and monitor context window usage across your AI development sessions.

Code for the paper "Language Models are Unsupervised Multitask Learners"

基于越狱数据集微调LLM会发生什么？

open source interpretability platform 🧠

The cryptography-based networking stack for building unstoppable networks with LoRa, Packet Radio, WiFi and everything in between.

Automatic Exploit Generation with LLMs

A collection of daily coding challenges designed to help you master idiomatic Go through deliberate, repetitive practice.

Fast CVVDP implementation in C

🗃 Open source self-hosted web archiving. Takes URLs/browser history/bookmarks/Pocket/Pinboard/etc., saves HTML, JS, PDFs, media, and more...

Sysbench scripts to generate a tpcc-like workload for MySQL and PostgreSQL

Dump complex C declarations visually.

Protect against malicious open source packages 🤖

The procedural generation voxel engine

Experimental library integrating LLM capabilities to support causal analyses

A Python library that helps data scientists to infer causation rather than observing correlation.

Large Language Models for Anomaly and Out-of-Distribution Detection

Knowledge Computing group - MSRA

漏洞赏金猎人指南 (Bug Bounty Hunter Guide)。

Code for ACL 2024 paper: PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models.

🤫 Code and benchmark for our ICLR 2024 spotlight paper: "Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory"

Dochia automatically generates and executes negative and boundary testing so you can focus on creative problem-solving. Because nobody wants to debug why their "enterprise-grade" API can't handle a…