Ensuring LLM Safety for Production Applications with Shreya Rajpal - #647
2023-09-18 · 41 min · episode 647 · 14 entities
Asserted relationships
-
→ appeared on The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence podcast0.68 · ×2
evidence rules-v4
Ensuring LLM Safety for Production Applications with Shreya Rajpal - #647
-
0.55 · ×2
evidence rules-v4
Feed author/publisher: Sam Charrington
-
0.40 · ×2
evidence rules-v4
Feed category: News
-
0.40 · ×2
evidence rules-v4
Feed category: Technology
-
0.40 · ×2
evidence rules-v4
Feed category: Science
-
0.40 · ×2
evidence rules-v4
Feed category: Tech News
-
0.40 · ×2
evidence rules-v4
Feed author/publisher: TWIML
Entities found in this episode
concepts 6
-
0.50 · ×2
evidence rules-v4
Feed category: Science
-
0.50 · ×2
evidence rules-v4
Feed category: Tech News
-
0.40 · ×2
evidence rules-v4
Feed category: News
-
0.40 · ×2
evidence rules-v4
Feed category: Science
-
0.40 · ×2
evidence rules-v4
Feed category: Tech News
-
0.35 · ×2
evidence rules-v4
LLM
companys 4
-
0.70 · ×2
evidence rules-v4
Feed author/publisher: TWIML
-
0.50 · ×2
evidence rules-v4
Feed category: Technology
-
0.40 · ×2
evidence rules-v4
Feed category: Technology
-
0.40 · ×2
evidence rules-v4
Feed author/publisher: TWIML
persons 3
-
0.72 · ×2
evidence rules-v4
Ensuring LLM Safety for Production Applications with Shreya Rajpal - #647
-
0.70 · ×2
evidence rules-v4
Feed author/publisher: Sam Charrington
-
0.55 · ×2
evidence rules-v4
Feed author/publisher: Sam Charrington
podcasts 1
-
appeared on The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence podcast0.68 · ×2
evidence rules-v4
Ensuring LLM Safety for Production Applications with Shreya Rajpal - #647
Episode description as stored
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.