๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

Julia Neagu
@juliaaneagu
AI research @Databricks @DbxMosaicAI | founded @QuotientAI โœจ formerly @GitHub @GitHubCopilot ๐Ÿค– reformed physicist ๐Ÿ‘ฉโ€๐Ÿ”ฌ ~ opinions are my own ~
๊ฐ€์ž… March 2013
2K ํŒ”๋กœ์ž‰ ์ค‘    3.8K ํŒฌ
We found that improving data agent quality also improves efficiency. Sometimes more is less: agents that take long, exploratory random walks are often less likely to arrive at the right answer. We put Genie Code head-to-head against three leading general-purpose coding agents on 400+ real user data tasks. Result below ๐Ÿ‘‡
๋” ๋ณด๊ธฐ