I ran into problems trying to deploy AI agents in the wild because people were trying to hijack and jailbreak them. As a result, I started researching and have begun working on a tool to scan LLM system prompts for vulnerabilities so that they can be fixed pre-deployment or at least anticipated. I'm currently taking baby steps by pulling together various tools from the open-source domain and trying to make them easy to use.

It's completely free for now. The report gets emailed to you within 24 hours.

https://tano-ai-security-tano.vercel.app/

The Gemini Technical Report is now up on Arxiv

Demo: https://llemma-demo.github.io/ Paper: https://arxiv.org/abs/2310.10631

Free. No sign-ups.

Built with React/Next/MongoDB/Heroku/GPT3.5

An easy and fun project to test out the capabilities of language models and try out some frontend frameworks at the same time.

Picked those figures because they have the most writing available for fine-tuning. Shakespeare is there because he has a very distinct style.

Sample responses:

Does free will exist? - Nietzsche https://philosophy.fyi/gen?id=63b14298fbda440e2d4d836c

How's it going? - Shakespeare https://philosophy.fyi/gen?id=63b219681778e270f01f7047

Empty prompt: https://philosophy.fyi/gen?id=63b217581778e270f01f7044