Y Hacker News new | ask | show | jobs

user: alexcombessie created: 2021-10-13 karma: 32 Co-Founder & CEO @ Giskard | Red-teaming platform for LLM agents submissions: LLM Sycophancy: The Risk of Vulnerable Misguidance in AI Medical Advice 2 points | 0 comments Agentic Tool Extraction: Multi-turn attacks that expose AI agents 1 points | 0 comments 0 points | 0 comments LMEval: An Open Source Framework for Cross-Model Evaluation 2 points | 0 comments 0 points | 0 comments 0 points | 0 comments Show HN: Open-Source Evaluation and Testing for Computer Vision Models 3 points | 0 comments Vision AI model vulnerability scan 1 points | 0 comments AI Systems Security: Top Tools for Preventing Prompt Injection 2 points | 0 comments Scanning LLM app vulnerabilities: Quickstart 1 points | 0 comments Evaluating LLMs with Giskard in MLflow 1 points | 0 comments Show HN: Automatic generation of LLM guardrails with NeMo and Giskard 1 points | 0 comments Coursera on Red Teaming LLM Applications 15 points | 1 comments Open-source AI projects selected by GitHub accelerator 10 points | 1 comments Show HN: Open-Source RAG Evaluation Toolkit 6 points | 0 comments LLM Red Teaming 101: Master the basics 3 points | 0 comments Open-Source Quality Management for AI Models 2 points | 0 comments 0 points | 0 comments 0 points | 0 comments