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

Steve โ€ข Plus
@steveDOTplus
Steve + AI ... busier than ever! ๐Ÿคฏ ๐Ÿ‡ฆ๐Ÿ‡น๐Ÿ‡ฌ๐Ÿ‡ง๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡ช๐Ÿ‡ช๐Ÿ‡ฎ๐Ÿ‡ช
๊ฐ€์ž… September 2024
891 ํŒ”๋กœ์ž‰ ์ค‘    100 ํŒฌ
Easy to shrug Jev off as just a classifier. The real leap is that it generalizes where older encoder models stayed special-purpose. ๐Ÿ‘€ #AI#
Itโ€™s easy to dismiss Jev it as โ€œjust a classifierโ€. But people (me included) who have been training encoder-style models for classification for many years know they were usually special-purpose and limited in some way. The breakthrough of Jev is that it generalizes well. And Iโ€™d say the secret sauce is probably more in the data than in the training algorithm. (Plus a nice API design on top of it.)
๋” ๋ณด๊ธฐ