2671 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
Some people spend Christmas Eve in a very Chinese way. The display board beside him reads:
"Resisting the U.S. and Aiding North Korea
Commemorating the 74th Anniversary of the Chinese People's Volunteer Army's Resistance to the US in Korean War
There is no Christmas Eve in
时政
(
twitter.com)
Many have pointed out this is not a Japanese metro station but the Xi'erqi station in Beijing. It is one of the busiest stations during business hours, and here is a video of it from Chinese social media.
Classical Western stereotyping: everything that's nice must be Japanese,
时政
(
twitter.com)
I've verified from reliable sources. New visual Turing Test: this is a real robot demo! The controller is a neural net trained in Isaac simulator using reinforcement learning and then sim2real. Reward engineering is all you need.
Walking gait's got swag but we need these robots
时政
(
twitter.com)