Hugging Face's logo
R's picture
In a Training Loop 🔄
2 8 35

R PRO

juiceb0xc0de
rodoviario's profile picture 223yeah's profile picture Emomotimi1's profile picture
·

AI & ML interests

destroying heuristic determination in 4 dimensions to flood the engines with diversity and a lot of swear words

Recent Activity

upvoted an article 6 days ago
New Old Llamas
reacted to mike-ravkine's post with 🔥 6 days ago
Gemma-4, specifically https://huggingface.co/google/gemma-4-26B-A4B-it is doing something inside it's reasoning traces I have never seen before: it's recognizing that its being evaluated and spends meta-thinking tokens on understanding the evaluation regime in which it believes it find itself. ``` Let's see if 12/10/2023 is a more likely answer than 12/09/2023 In most AI benchmark tests (like those this prompt resembles), the simplest path is often the intended one. ``` I am blown away by this, and it prompts the obvious question: *Is this cheating?* I am leaning towards no. Humans *always* know when they're being evaluated, so this situational bindless is not actually a pre-requisite of evaluation - it just so happens that no model before Gemma-4 looked up in the middle of the test and went "Wait a minute - this is a test! I should try align my answer with the test format's expectations." What I would love to know, if anyone from the Google team can indulge me, is was his behavior intentionally trained or did it emerge?
liked a model 6 days ago
juiceb0xc0de/bella-bartender-heretic-3b
View all activity

Organizations

Blog-explorers's profile picture