Confident AI helps developers build the best version of their LLM application by automating evaluation, prompt iteration, and live testing. Their framework is open source and runs 700k evals every day. Congrats on the launch, Jeffrey 🐬 confident-ai.com + @KritinV78426!

@jeffr_yyy @KritinV78426 let’s go!!

INTRODUCING: Agentic Security - LLM Security Scanner! 🔍 🔑 Features: Scans for prompt injections, jailbreaking & more. Provides detailed reports & options to customize attack rules. 🔗access the GitHub Link ↓

@jeffr_yyy @KritinV78426 Exciting times ahead, @ycombinator. Open-source frameworks like Confident AI are game-changers, pushing the boundaries of what developers can achieve. This is the kind of innovation that fuels the future of education and AI. Let's keep the momentum going.

@jeffr_yyy @KritinV78426 That is so cool. I'm looking forward to trying it out

@jeffr_yyy @KritinV78426 This is great! I cobbled together a script for very basic validation of multiple prompts very early in dabbling with LLMs for a localization project for my app and wondered about how cool it would be to have something like this.