$ cat /etc/cookies.conf
We use cookies to understand how people use this site.
Analytics cookies help us improve your experience.
They are off by default. Nothing tracks you until you say so.
$ select cookie_preferences
Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Learn to build a DSPy classification pipeline: load data, evaluate a base model, apply optimization, and compare results to a prompt‑only approach.
Learn by example to use DSPy and write AI programs, not prompts
I will pick a classification task and walk through a DSPy program that loads evaluation data, evaluates a base classifier, optimizes the classifier and then evaluates the optimized classifier.
I will highlight how the DSPy approach differs from having a big long string as the prompt.
DSPy code classifies Quora sincerity using Gemini, optimizing few-shot compilation.
Loading recent emails...