Lists (1)
Starred repositories
A minimal hardware-software architecture giving large language models a closed-loop physical embodiment with self-perception loops.
Crowdsourced, inline LLM investigations of the things you're reading.
VSCode theme based off the easemate IDE and Jetbrains islands theme
Recovered cia.gov/the-world-factbook/about/archives/download/factbook-2020.zip from Internet Archive
Making open safety AI models accessible and beneficial to the safety community
Companion repository to the Fuzzing101 with LibAFL series of blog posts.
MCP to help Defenders Detection Engineer Harder and Smarter
Directory of open source tools for online safety
An alignment auditing agent capable of quickly exploring alignment hypothesis
An open-source command-line tool for cybersecurity reporting automation and a configuration language for reusable templates. Reporting-as-Code
A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focuses on modern AI technologies like Large Language Models (LLMs), Agents, and Multi-Moda…
Data about all known supply-chain attacks through history
explore token trajectory trees on instruct and base models
An encyclopedia of jailbreaking techniques to make AI models safer.
A knowledge source about TTPs used to target GenAI-based systems, copilots and agents
Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
A tool to scan websites for chatbot functionality
Every practical and proposed defense against prompt injection.
Representation Engineering: A Top-Down Approach to AI Transparency
Dictionary of attack patterns and primitives for black-box application fault injection and resource discovery.
A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.