esbenkc

esbenkc's Stars

• SWE-agent/SWE-agent

  SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

  Language:Python14k1003951.4k

• rougier/scientific-visualization-book

  An open access book on scientific visualization using python and matplotlib

  Language:Python10.8k19043993

• GreyDGL/PentestGPT

  A GPT-empowered penetration testing tool

  Language:Python7.4k119140904

• smol-ai/GodMode

  AI Chat Browser: Fast, Full webapp access to ChatGPT / Claude / Bard / Bing / Llama2! I use this 20 times a day.

  Language:TypeScript4.2k42161329

• EasyJailbreak/EasyJailbreak

  An easy-to-use Python framework to generate adversarial jailbreak prompts.

  Language:Python51783041

• jzhang38/LongMamba

  Some preliminary explorations of Mamba's context scaling.

  Language:Python20215412

• rgreenblatt/arc_draw_more_samples_pub

  Draw more samples

  Language:Python1816324

• METR/task-standard

  METR Task Standard

  Language:TypeScript1316931

• centerforaisafety/wmdp

  WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining general capabilities.

  Language:Jupyter Notebook8811224

• METR/public-tasks

  Language:TeX70503

• andyzorigin/cybench

  Language:HTML653938

• schroederdewitt/perfectly-secure-steganography

  Contains open source code for the paper "Perfectly-secure Steganography using Minimum Entropy Coupling"

  Language:Python48428

• thestephencasper/everything-you-need

  we got you bro

  34100

• callummcdougall/sae_visualizer

  Language:HTML24411

• Mindgard/cli

  Test your AI model's security through CLI

  Language:Python20522

• noemaresearch/pinboard

  Pin files for contextual, codebase-level AI assistance.

  Language:Python15301

• camtice/SandbagDetect

  Language:Jupyter Notebook61

• nlpet/democracy-ai-hackathon

  This repository contains code for the Democracy x AI Hackathon by Apart Research

  Language:Jupyter Notebook6102

• apartresearch/evaluations-starter

  How to get started in evaluations and demonstrations research for dangerous capabilities

  5221

• apartresearch/Research-Augmentation-Hackbook

  Language:Python5100

• apartresearch/3cb

  3cb: Catastrophic Cyber Capabilities Benchmarking of Large Language Models

  Language:Python441

• matthewjlutz/MASec-info-flow

  Python code for "Fishing for the answer: Mapping the flow of information in LLM agent groups using lessons from fish schools" submitted to Apart Research Multi-Agent Security Hackathon 2024.

  Language:Python4200

• esbenkc/karnak

  🔐 Make sure AI applications are not injecting 1) suspicious API calls, 2) vulnerabilities, and 3) rogue capabilities

  Language:JavaScript3100

• esbenkc/cyberwarfare

  🤝 Cyberwarfare vulnerabilities for democracy

  Language:Python220

• Lovkush-A/inspect_multiturn_dialogue

  Language:Jupyter Notebook2100

• apartresearch/hackathon-utils

  😎 Code to run hackathons efficiently

  Language:HTML110

• apartresearch/task-standard

  🚨 METR Task Standard fork for the Code Red Hackathon

  Language:TypeScript100

• lennart-finke/picturebooks

  Which objects are visible through the holes in a picture book? This visual task is easy for adults, doable for primary schoolers, but hard for vision transformers.

  Language:Jupyter Notebook1100

• simonwisdom/public-comment-generator

  Language:JavaScript1

• timothee-chauvin/PrimeVul-assets-on-github

  PrimeVul with the assets under version control on github, not on google drive

  Language:Python1000