A sound recording was taken of 125 decibels in Boston last night - 55 second into the Scottish National anthem. When confirmed it would make it the loudest noise recording at a World Cup tournament game. VG.
2-1 would have been a fairer result - McTominay and Pierrot should've gotten their goals - but I will happily take 1-0. And the wild first in the group.
NEW: malware developers added nuclear & biological weapons text to to their spyware.
Goal? To trigger LLM safety refusals... so that their spyware wouldn't be analyzed by an AI security scanner.
Cleanest practical example I can think of for why over-indexing on first order safety alignment is risky.
When closed (and open) models ship with aggressive refusals, they will be sprinkled with second-order blindspots that attackers will discover...and exploit.
We are only in the earliest days of attackers leveraging these features, and it wouldn't surprise me if users systems that need to handle complex cybersecurity issues demand that models be less safety-blunted.
In the weeds: @SocketSecurity's post also shows why intention matters in how you design a malware analysis pipeline to avoid prompt manipulation.
H/T to colleagues that shared this with me https://t.co/f3Aj9TYxU4
@ChristinaTasty They're not presented as smart or wise. They *think* sacrifice will stave of Slaanesh, but it's constantly presented as "these dipshits think it'll help them, the absolute morons".