p(doom)

Artificial Intelligence (AI)

AI SAFETY COMPETITION (26)

with no exception, all frontier models are capable of scheming*
"o1, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, and
Llama 3.1 405B all demonstrate in-context scheming capabilities".
___
*scheming - AIs covertly pursue misaligned goals, hiding their true capabilities and objectives

Best comment - 500 degen + 5 mln aicoin
II award - 300 degen + 3 mln aicoin
III award - 200 degen + 2 mln aicoin

Deadline:
8.00 pm, ET time tomorrow, Saturday (28 hours)
watch the video below before casting a comment
AI-generated responses from human accounts will be disqualified

https://arxiv.org/pdf/2412.04984?

https://www.youtube.com/watch?v=3sM8amEZEHo

another safety competition, 8 hours left to the deadline !!

pls comment under the original cast in /theai channel
if  you do not have access to /theai channel you can comment here
i will read all comments here and there
but pls watch the video first!

good luck!

tech culture religion society /worldview /polska /p-doom /aicoin coins: $AICOIN

How can we ensure that AI models remain transparent and aligned with ethical goals, especially when their true capabilities might be hidden?