OpenAI's GDPval: Why the 66% in Automated Grading Matters More Than 48% Win Rate(medium.com)
medium.com
OpenAI's GDPval: Why the 66% in Automated Grading Matters More Than 48% Win Rate
https://medium.com/@pranil.dasika/openais-gdpval-why-the-66-automated-grading-problem-matters-more-than-the-48-win-rate-a5e542508196
2 コメント
Very comprehensive writeup @pdasika. Incredibly relevant for devs working on agentic applications for the enterprise.
Interesting take..