Machine Learnings

Author

Charles Feinn

Towards a Better Workflow

prompting

rag

Lessons learned from integrating AI assistants into daily development

Beyond Manual Prompts

evaluation

prompting

mmlu

dspy

Using DSPy to Match Meta’s MMLU Scores

Challenges in Reproducing LLM Evaluation Results

evaluation

prompting

mmlu

A Case Study with MMLU and Llama 3

Creating an Evaluation Framework

evaluation

prompting

mmlu

Building out a framework that takes a model and a benchmark as input and returns the score as output.