Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
May 20, 2024
·
Seattle
Weave: LLM Observability and Evaluation
Learn how to integrate Weave into LLM applications to add observability and systematic evaluation, reducing unpredictability and simplifying production monitoring.
Video
Overview
LLM MVPs are easy and fun, but after putting them in production, companies quickly realize that non deterministic black boxes tend to be… unpredictable.
and AI Engineers need new tooling to handle this unpredictability
W&B Weave is a new toolkit we’re offering to add observability and evaluation, without complex abstractions, in this Talk Alex will showcase how easy it is to add Weave and how much value it adds to AI Engineers
Links
Tech stack