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

Jennifer Zhou
@chem_safety
rl data @preferencemodel | prev pretraining data @AnthropicAI
๊ฐ€์ž… December 2023
427 ํŒ”๋กœ์ž‰ ์ค‘    2.1K ํŒฌ
Today we are open-sourcing ๐Ÿฅ•Karotte, our framework for building RL environments. We've used it for the past year to build MLE RL environments for frontier labs, and it's been hardened through 1M+ evaluation runs and red-teaming.
๋” ๋ณด๊ธฐ