![The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) artwork](https://is1-ssl.mzstatic.com/image/thumb/Podcasts113/v4/39/58/c6/3958c6ce-86e4-3b80-bfb9-840e1dfd7e4b/mza_491361902049110775.png/100x100bb.jpg)
Ensuring LLM Safety for Production Applications with Shreya Rajpal - #647
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
English - September 18, 2023 18:17 - 40 minutes - ★★★★★ - 323 ratingsTechnology News Tech News machinelearning artificialintelligence datascience samcharrington tech technology thetwimlaipocast thisweekinmachinelearning twiml twimlaipodcast Homepage Download Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed
Today we’re joined by Shreya Rajpal, founder and CEO of Guardrails AI. In our conversation with Shreya, we discuss ensuring the safety and reliability of language models for production applications. We explore the risks and challenges associated with these models, including different types of hallucinations and other LLM failure modes. We also talk about the susceptibility of the popular retrieval augmented generation (RAG) technique to closed-domain hallucination, and how this challenge can be addressed. We also cover the need for robust evaluation metrics and tooling for building with large language models. Lastly, we explore Guardrails, an open-source project that provides a catalog of validators that run on top of language models to enforce correctness and reliability efficiently.
The complete show notes for this episode can be found at twimlai.com/go/647.
Today we’re joined by Shreya Rajpal, founder and CEO of Guardrails AI. In our conversation with Shreya, we discuss ensuring the safety and reliability of language models for production applications. We explore the risks and challenges associated with these models, including different types of hallucinations and other LLM failure modes. We also talk about the susceptibility of the popular retrieval augmented generation (RAG) technique to closed-domain hallucination, and how this challenge can be addressed. We also cover the need for robust evaluation metrics and tooling for building with large language models. Lastly, we explore Guardrails, an open-source project that provides a catalog of validators that run on top of language models to enforce correctness and reliability efficiently.
The complete show notes for this episode can be found at twimlai.com/go/647.