- TU Wien
- Vienna, Austria
- 15:08
(UTC +01:00) - https://orcid.org/0009-0009-5796-2992
- in/pnormann
Highlights
- Pro
Stars
BenchBench is a Python package to evaluate multi-task benchmarks.
Framework to capture realistic cyberattacks in controlled, containerized environments. Automatic network traffic capturing, processing and fine-grained labeling. Built on top of Kubernetes.
Implement a reasoning LLM in PyTorch from scratch, step by step
Agentic malware analysis environment with MCP-connected disassemblers, RE tooling, and structured workflows for Claude Code and Codex CLI.
Fast and memory-efficient exact kmeans
GTFOBins is a curated list of Unix-like executables that can be used to bypass local security restrictions in misconfigured systems.
Hydra is a framework for elegantly configuring complex applications
Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.
Build cross-language call graphs for Python packages. Perform vulnerability reachability analysis, detect unused code (bloat)
Malware Configuration And Payload Extraction
Infrastructure for capturing LLM activations and SAE (Sparse Autoencoders) features, training probes for prompt maliciousness detection, and evaluating out-of-distribution generalization with Leave…
An open-source benchmark for evaluating AI agents' ability to find backdoors hidden in compiled binaries.
[NeurIPS 2024 / ICML 2025] LLM Quantization Attacks
This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.
Optimize prompts, code, and more with AI-powered Reflective Text Evolution
Post-training with Tinker
A lightweight, lightning-fast, in-process vector database
OpenTofu lets you declaratively manage your cloud infrastructure.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Archive a lifetime of email and chat. Offline search, analytics, and AI query over your full message history. Powered by DuckDB
Generative Modeling via Drifting in MLX
Generate High-Quality Synthetics, Train, Measure, and Evaluate in a Single Pipeline
Render markdown on the CLI, with pizzazz! 💅🏻
A 5-20x faster experimental Homebrew alternative
