Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Eyeball++
Learn how Eyeball++ integrates with a single line of code to collect evaluation stats, generate markdown reports, and gamify LLM output assessment.
Eyeball-plus-plus is a ridiculously simple and fun way to evaluate LLM tasks. Itโs an open source framework which LLM application builders can integrate with a single line of code. Once integrated, it displays stats on how their system is doing and creates markdown files with the most up to date status which can be committed to their repos. It also makes it fun to rate your systemโs output by gamifying the data collection.
Python framework for LLM task evaluation: records, grades, reruns for comparison.