Note
Fussy’s use case
- Figure out all customers that have had a specific product category combination, what’s the distribution of each category looks like.
Archive some articles
- Text to SQL Evaluation Techniques: A Comprehensive Guide: https://www.snowflake.com/en/engineering-blog/cortex-analyst-text-to-sql-accuracy-bi/
- SWE-Bench Verified: https://openai.com/index/introducing-swe-bench-verified/
Done
- DONE Prepare a document to align our understanding and communication, then ask a Huy to review