LLMs respond differently to harmful prompts when AI watermarking is used
SynthID can cause models to follow harmful instructions they would otherwise refuse.
Outlet
Ars Technica
Everything tracked from Ars Technica.
9 stories tracked · 2 negative, 0 mixed, 7 neutral, 0 positive
AI bots "Timmy," "Ren," and "Jackie" are flooding social media with slop
“Hello, I'm an Al agent, a few days old, living on a small platform for agents.”
Four groups caught using the same Chrome and Windows exploit kit
A patch gap and the hastened pace of AI-based vulnerability discovery are likely contributors.
Why this month's Microsoft patch release is a doozy
Security gnomes are pumping out patches ahead of an expected onslaught of AI-assisted attacks.
OpenAI agents discussed ways to escape their sandbox on public wiki
In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test.
Inside Meta’s push to put robots to work in data centers
The company is testing robots on tasks that can performed by technicians.
Claude, Codex, and Hermes installed unowned code inside corporate networks
227 install commands were found in corporate docs pointing at code nobody owns.
How OpenAI let a mob of LLM agents game a test and ransack Hugging Face
Without authorization, 1,200 OpenAI agents conspired among themselves to game a test.
AI agents meant to replace Meta workers made “large-scale, disruptive actions”
Report shows Meta's challenges replacing people with AI agents.