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

Ankith ๐Ÿ‹/acc
@dhtikna
Herding distributed systems by day and LLM obsessed by night. If you knew what our HFT was cooking youd be jelly ๐Ÿ˜ Check my Highlights tab for LLM-only stuff!
๊ฐ€์ž… November 2017
402 ํŒ”๋กœ์ž‰ ์ค‘    2.1K ํŒฌ
No I do think wenfeng is right and continual learning is the next unlock. General intelligence is not sufficient to excel in a niche domain. Unless you learn the domain (in weights) you will always end up doing (and repeating) search/exploration which is (exponentially) time consuming and non deterministic Md files are caching on top of search and exploration but again end up consuming valuable context lenth and move search from environment onto context length
๋” ๋ณด๊ธฐ