3872 位用户此时在线
- 本站自动实时分享网络热点
- 24小时实时更新
- 所有言论不代表本站态度
- 欢迎对信息踊跃评论评分
- 评分越高，信息越新，排列越靠前
I'm more and more confident that tokenization will be gone.
Humans don't think in "tokens".
Tokens are hardcoded abstractions in LLMs that lead to weird behavior: LLMs can solve PhD-level math questions but cannot answer "Is 9.9 > 9.11?"
Meta is shifting LLMs to LCMs (Large
时政
(
twitter.com
)
I'm more and more confident that tokenization will be gone.
Humans don't think in "tokens".
Tokens are hardcoded abstractions in LLMs that lead to weird behavior: LLMs can solve PhD-level math questions but cannot answer "Is 9.9 > 9.11?"
Meta is shifting LLMs to LCMs (Large Concept Models), changing "next-token prediction" to "next-concept prediction". A "concept" is treated as a sentence, representing an abstract idea or action.
Two weeks ago, Meta also published the "Byte Latent Transformer", a new architecture that processes raw bytes grouped into patches instead of relying on tokenization.
My intuition says LCM is probably better at reasoning and modalities.
点击图片查看原图
Today, we can already say there is a good result for our air defense – Ukraine now has more Patriots. I thank Chancellor Merz, I thank Germany, and everyone who helps – our agreements have been fulfilled. More Patriots are now in Ukraine and being put into operation.
Of course,
时政
(
twitter.com)
Google Veo 2 art testing. "THE GOAT IS BACK" - Chinese Shui-mo Style. Overall, Veo 2 is strongly capable of prompt following, e.g. "misty jungle", "fog", "wild life" etc., and I strongly recommend its dolly zoom. All PIXEL GENERATED FROM TEXT by Veo2, sound is added manually.
时政
(
twitter.com)