Framework
Evaluation (evals)
A method of testing how well AI models perform on specific tasks, akin to quizzes for assessing knowledge.
Preparing graph…
100%
Framework
Evaluation (evals)
1 visible of 1 connections
8 nodes · 7 connectionsConceptEpisodeFrameworkPersonPracticeLarger = more connections+ Expand · − Collapse (double-click)Drag a node to pull its neighbors along
Episodes1
Related Concepts3
Related Practices2
Transcript mentions
… actually follow this thread on evals. I definitely wanted to talk about this.
🛠️
Framework
Evaluation (evals)
A method of testing how well AI models perform on specific tasks, akin to quizzes for assessing knowledge.
Episodes1
Related Concepts3
Related Practices2
Transcript mentions
… actually follow this thread on evals. I definitely wanted to talk about this.