3117 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
Elon Musk: One platform can change everything.
“As soon as any company steps out of line and is willing to actually have the truth debated on their platform, it forces the other platforms to be more truthful, to not censor.
Because their censorship becomes glaringly obvious.”
btc
(
twitter.com)
OpenAI Sora was out of the game on day one.
To be fair, I compared it with Hunyuan, which dropped 6 days ago, it's an open-source AI model and you can run it locally for free.
TBH, if I were to compare it to Hailuo AI or Kling AI, Sora would look even worse.
Let’s dive in:
时政
(
twitter.com)