Lists (1)
Stars
System-level security for LLM agents: fine-grained policy enforcement on tool calls to defend against indirect prompt injection
A minimal, secure Python interpreter written in Rust for use by AI
Inspect: A framework for large language model evaluations
Training Sparse Autoencoders on Language Models
Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University
Working, locally-running, low-cost implementation of Generative Agents: Interactive Simulacra of Human Behavior.
The hub for EleutherAI's work on interpretability and learning dynamics
Code repository for "Eliciting Secret Knowledge from Language Models"
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
Flow Integrity Deterministic Enforcement System. Mechanisms for securing AI agents with information-flow control.
A compilation of the best multi-agent papers
A guidance language for controlling large language models.
AeroSpace is an i3-like tiling window manager for macOS
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Zero instrucment LLM and AI agent (e.g. claude code, gemini-cli) observability in eBPF
Rex is a safe and usable kernel extension framework that allows loading and executing Rust kernel extension programs in the place of eBPF.
The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)
Free, no-nonsense, super fast blogging.