hwchase17 / adversarial-prompts
Curation of prompts that are known to be adversarial to large language models
☆174Updated last year
Related projects ⓘ
Alternatives and complementary repositories for adversarial-prompts
- Red-Teaming Language Models with DSPy☆142Updated 7 months ago
- Camel-Coder: Collaborative task completion with multiple agents. Role-based prompts, intervention mechanism, and thoughtful suggestions☆33Updated last year
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆313Updated 8 months ago
- Test suite for LLM prompts☆39Updated 6 months ago
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆86Updated 5 months ago
- Code for the website www.jailbreakchat.com☆74Updated last year
- 🔓 The open-source autonomous agent LLM initiative 🔓☆90Updated 9 months ago
- GPT-based Conversation Summarizer☆147Updated last year
- ☆172Updated last year
- ☆240Updated 4 months ago
- Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!☆259Updated last month
- Meta-prompt: a simple self-improving language agent☆88Updated last year
- A Toolkit for Creating and Deploying LangChain Apps☆168Updated last year
- ☆219Updated last year
- A trace analysis tool for AI agents.☆124Updated last month
- Just a bunch of benchmark logs for different LLMs☆115Updated 3 months ago
- ☆266Updated last year
- Code for Parsel 🐍 - generate complex programs with language models☆417Updated last year
- A strongly typed Python DSL for developing message passing multi agent systems☆50Updated 7 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆186Updated this week
- Code and data for "Measuring and Narrowing the Compositionality Gap in Language Models"☆299Updated 10 months ago
- ☆106Updated last year
- Directly Connecting Python to LLMs via Strongly-Typed Functions, Dataclasses, Interfaces & Generic Types☆388Updated last month
- A set of utilities for running few-shot prompting experiments on large-language models☆113Updated last year
- A simple wrapper for OpenAI to log input/outputs.☆103Updated last year
- This shows the results from using a second, filter LLM that analyses prompts before sending them to GPT-Chat☆106Updated last year
- Interactive Composition Explorer: a debugger for compositional language model programs☆535Updated last month
- Reimplementation of the task generation part from the Alpaca paper☆119Updated last year
- This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious c…☆221Updated last year
- ☆75Updated 9 months ago