CYBERWAVE 1984 // Synthwave ~ Chillsynth https://t.co/iR8HD7JfKX via @YouTube
1984 was a good year for vibes. The newspeak didn't end up being that bad. Most of the negativity was just problematic misinformation.
@GrimGriz We’re wrestling with complications using strength who is also the goat. עזניה
And Azazel-adjacent.
Where is the conflict, there we find the properly ordered new beings.
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
@GrimGriz@SteveSkojec Unless Khandahar giants are Langoliers who have joined the International Communist Party. Wake up sheeple. Saturn is the real Red planet. Connection? What, are you working for *them*?
@PageauJonathan@GrimGriz Many little girls eventually become grandma so if the wolf is inversion it should move backwards through stages of enticement. Also uninverted wolves hunt, so inverted wolves lie in wait for food to fall into their mouth. Like a spider. Do an episode on why wolves aren’t spiders.
Users who interact with a misleading post that is subsequently corrected by @CommunityNotes will receive an 𝕏 Chat message of the CN to correct any misperception
There will not be a "last summer". There will not be a "permanent underclass". There will not be "human extinction". There will not be "endless suffering".
We are going to make it. Not because it's easy, but because it's possible. Because we can. Because we care enough to try