WIREDLean L·
It’s Frighteningly Easy to Jailbreak Some Frontier AI Models
I watched a new tool try to get around the model safeguards of four major frontier companies. You might be surprised by how they performed.
Read at WIRED →
Technology · 1 sources covering this
It’s Frighteningly Easy to Jailbreak Some Frontier AI Models
I watched a new tool try to get around the model safeguards of four major frontier companies. You might be surprised by how they performed.
Coverage spectrum
1 L · 0 C · 0 R
How 1 sources are covering this
Embed this bias spectrum on your site
Paste this iframe wherever you'd like the widget to appear. Resizes responsively; no JS required.
<iframe src="https://statesidedaily.com/embed/cluster/8cda295ca108b8399dc2bc90e51f961ff445db34" width="100%" height="320" style="border:0;max-width:680px" loading="lazy" title="It’s Frighteningly Easy to Jailbreak Some Frontier AI Models"></iframe>
