To train or not to train your LLM

What's in this video

• This webinar recording from July 2023 examines decisions teams faced when bringing LLMs into business applications.
• It asks when prompt engineering is enough to reach the accuracy an application needs.
• It considers data-sharing choices when teams use an outside model provider.
• Gad Benram of TensorOps presents three reasons to train an LLM and three reasons to use an out-of-the-box model.

Related Videos

37:32

Machine learning observability essentials (webinar)

Learn ML monitoring, anomaly detection, and data-driven retraining practices that help teams detect drift and maintain reliable model performance.

Watch on its own page

35:33

Meet Elemeta: metafeature extraction for unstructured data

Explore how open-source metafeature extraction turns text and images into structured information for document processing and AI applications.

Watch on its own page

15:46

AgentCon 2025: SUPERWISE live demo

Watch the SUPERWISE AgentCon 2025 demo of AI guardrails that prevent data leakage and protect sensitive data in production agent workflows.

Watch on its own page

1:26:46

LLM optimization beyond fine-tuning

Watch a February 2024 webinar on prompt optimization, evaluation, RAG techniques, model pruning, quantization, semantic caching, and edge deployment.

Watch on its own page

1:07:18

Prompt engineering methods for LLMs

Watch an October 2023 webinar on matching prompts to LLM tasks, prompt formats, thought frameworks, chaining, and bug-driven development.

Watch on its own page

55:18

Architectures for LLM applications

Watch an August 2023 webinar on embeddings, vector databases, prompt construction, retrieval, inference, evaluation, and hosting for LLM applications.

Watch on its own page

Explore more AI governance resources

Explore AI governance insights, platform resources, implementation guidance, and customer stories.