LLM Sycophancy: The Risk of Vulnerable Misguidance in AI Medical Advicegiskard.ai·2 pts·alexcombessie·0
LMEval: An Open Source Framework for Cross-Model Evaluationopensource.googleblog.com·2 pts·alexcombessie·0
Show HN: Open-Source Evaluation and Testing for Computer Vision Modelsgithub.com·3 pts·alexcombessie·0
Show HN: Automatic generation of LLM guardrails with NeMo and Giskarddocs.giskard.ai·1 pts·alexcombessie·0
AI Safety Research Outside the Hubs: A Guide for Aspiring Researchers – Videoyoutube.com·2 pts·alexcombessie·0
Show HN: Giskard – Testing framework dedicated to LLMs and Tabular ML modelsgithub.com·15 pts·alexcombessie·8
Awesome AI Safety – curated papers for safer, ethical, and reliable AIgithub.com·14 pts·alexcombessie·1
How to deploy a robust HuggingFace model for sentiment analysis into production?giskard.ai·3 pts·alexcombessie·0