← Latest products

I designed a ChatGPT prompt evaluator to ruin your fun;)

This shows the results from using a second, filter LLM that analyses prompts before sending them to GPT-Chat. Today I designed a method to prevent users from jailbreaking ChatGPT (for instance, users have generated instructions to produce weapons or illegal drugs, commit a burglary, kill oneself, take over the world as an evil superintelligence, or create a virtual machine which they then can use).

Open source

110 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. I made a chatbot that debugs your code better than ChatGPT

    useadrenaline.com

    I built this using semantic search and the ChatGPT API, which was just released the other day.

    Hacker News7 pts

  2. Hacker News GPT

    chat.openai.com

    Just a personal experiment to build my first custom version of ChatGPT :) I'm spending too much time on this site, so it might ocasionally save me some scrolling and reading.

    Hacker News11 pts

  3. ChatGPT Prompts and Products

    chatgpt.getlaunchlist.com

    Hacker News16 pts

  4. ChatGPT Plugins are a security nightmare

    github.com

    New ways of breaking app-integrated LLMs

    Hacker News238 pts

  5. Signal ChatGPT bot

    youtube.com

    with image generation and TTS [video]

    Hacker News12 pts