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

Alex Godofsky
@AlexGodofsky
Dad, husband, actuary. #pensions# "More like Mr. Goofsky"
๊ฐ€์ž… June 2011
750 ํŒ”๋กœ์ž‰ ์ค‘    7.2K ํŒฌ
re: interpretability, what if the bitter lesson eventually enables us (well, our LLMs) to decompose trained LLMs into explicit logical components that can be expressed in ordinary code ๐Ÿค”