Safe and Sound AI

Auteur(s): Fiddler AI
  • Résumé

  • Safe and Sound AI is your go-to podcast for staying ahead in predictive and generative AI development. From pre-production design and post-production monitoring to governance and compliance, we deliver bite-sized episodes packed with technical insights and best practices. Designed for data scientists, engineers, trust and safety teams, and business leaders, our focus is to help you deliver and scale AI innovations with safety, trust, and transparency in mind. Safe and Sound AI is brought to you by Fiddler AI.
    Copyright 2024 All rights reserved.
    Voir plus Voir moins
Épisodes
  • Tracking Drift to Monitor LLM Performance
    Dec 12 2024

    In this episode, we discuss how to monitor the performance of Large Language Models (LLMs) in production environments. We explore common enterprise approaches to LLM deployment and evaluate the importance of monitoring for LLM quality or the quality of LLM responses over time. We discuss strategies for "drift monitoring" — tracking changes in both input prompts and output responses — allowing for proactive troubleshooting and improvement via techniques like fine-tuning or augmenting data sources.

    Read the article by Fiddler AI and explore additional resources on how AI observability can help developers build trust into AI services.

    Voir plus Voir moins
    12 min

Ce que les auditeurs disent de Safe and Sound AI

Moyenne des évaluations de clients

Évaluations – Cliquez sur les onglets pour changer la source des évaluations.