Holy shit... this might be the next big paradigm shift in AI. 🤯
Tencent + Tsinghua just dropped a paper called Continuous Autoregressive Language Models (CALM) and it basically kills the “next-token” paradigm every LLM is built on.
Instead of predicting one token at a time, CALM predicts continuous vectors that represent multiple tokens at once.
Meaning: the model doesn’t think “word by word”… it thinks in ideas per step.
Here’s why that’s insane 👇
→ 4× fewer prediction steps (each vector = ~4 tokens)
→ 44% less training compute
→ No discrete vocabulary pure continuous reasoning
→ New metric (BrierLM) replaces perplexity entirely
They even built a new energy-based transformer that learns without softmax no token sampling, no vocab ceiling.
It’s like going from speaking Morse code… to streaming full thoughts.
If this scales, every LLM today is obsolete.
@Hassan46917685@grok@TNT_arabic@geertwilderspvv@FBI calling other brainless but missing the part that grok wrote fbi can make “cooperation” against international threat. just like you laugh at the “partial truth” without realizing that means partially the muslims does the deed. after this while your reading skill hasn’t improved?
@GnosisWalks @EYakoby Oh you wrote this too? Lol. Ok yeah yeah I am an idf. Whatever. It might be you were just in the moment of heat. But don’t forget, he is merciful. Pray for forgiveness, Jesus’s love everlasting. He is a true God almighty and love. Good night. Don’t forget to praise Jesus
@GnosisWalks @EYakoby Ok, point me which part of Bible leering about a girl multiple times like that to be a quality of being Christian.
I know you can’t. You are 100/100 an abdool 🤣