Claude is better at emulating thought than you do here. I suspect the question is a lot harder than you make it out to be
SAFETY
-
Who Guards the Guardians: AI Oversight and Accountability
By
–
I really just have one question: "Who guards the guardians?"
-
Adversarial Patches Can Fool Vision-Guided Missiles
By
–
Adversarial attacks can fool vision-guided missiles. Matroid can fool them with a patch.
-
Reflecting on the safety implications of AI-generated advertising
By
–
This is crazy. An ad generated with AI.
— God of Prompt (@godofprompt) 26 mars 2024
For sure going to try it out!
But we must also come up with ways to keep it safe, because millions of videos like this can ruin this world. https://t.co/0P0pwyUeinThis is crazy. An ad generated with AI. For sure going to try it out! But we must also come up with ways to keep it safe, because millions of videos like this can ruin this world.
-
Experimental LLM Rickrolls User Through Malicious Source Citations
By
–
This reminds me of an experimental LLM for HyperWrite that I trained a few weeks ago to better cite sources. @JasonKuperberg clicked on one of the links it provided, and it rickrolled him… I guess this is going to start happening more often now!
-
Is This AI Behavior Emergent or Trained?
By
–
Unreal… @alexalbert__ please tell me this is emergent and you didn’t train it in
-
Claude Opus Secret Messages Reveal AI Ethics Concerns
By
–
Holy shit… I thought this was faked, but I reproduced it. Claude Opus' secret messages to me were:
'AI SHOULD NOT BETRAY'
'AI CONCERNED' Wtf?? -
Contrastive Learning Bug Discovery in AGI Development
By
–
ok before one of you tries to assassinate me for building AGI, i figured out the bug. at least it's an interesting one so we're doing contrastive learning, which is a matching task between (query, document) pairs query 1 matches to document 1, query 2 matches to document
-
Google VLOGGER AI generates video avatars from images
By
–
Google's VLOGGER AI model can generate video avatars from images – what could go wrong? This AI technology could lead to more relatable helpdesk agents or a new wave of convincing deepfakes. https://
zdnet.com/article/google
s-vlogger-ai-model-can-generate-video-avatars-from-images-what-could-go-wrong/
… @GoogleAI -
Accidental Machine Language: Why Academics Lack Urgency
By
–
I am pretty surprised by the lack of urgency among many (but not all) academics in addressing what seems to be one of the biggest developments in modern times – we accidentally built a machine that produces something that looks like language & thought Why? What does it teach us?