GX Xu(@GX_NLP) 's Twitter Profile Photo

Even powerful LLM like Claude3 Opus breaks with the simplest attacks to start hallucinating about “non-existing” context about “steps”.

The kind of mistake that a human 5 year old wouldnt make. 😉

Even powerful LLM like Claude3 Opus breaks with the simplest attacks to start hallucinating about “non-existing” context about “steps”.

The kind of mistake that a human 5 year old wouldnt make. 😉
account_circle
khorie(@khanza_abigael) 's Twitter Profile Photo

ƗƗɐƗƗɐƗƗɐ '̮ ƗƗɐƗƗɐƗƗɐ ™ tidurr gihh syankk...udh jam 12...ak gx nlp lgi yaaa ... m.tmi.me/19l6Mu

account_circle
GX Xu(@GX_NLP) 's Twitter Profile Photo

TLDR: Looking for a RLHF method that combines the best of PPO and DPO, stable training, and gives amazing result?

BRAIN theoretically unites DPO and PPO, and empirical shown to out-perform!

An earlier pre-print of the ICML paper is available now🔥

account_circle
Jamileeh(@Amillah19) 's Twitter Profile Photo

Kataku dlm hati,'ngalir aja sih',, kmu gx nyapa aku jugak gx akan nyapa,, kmu gx nlp,chat dluan,,aku apa lgi,,
Realitanya,,klo sehari gx komunikasi,, mood kyak org PMS tiap hari,,,

Gini amat, gengsian

account_circle