Anthropic grants METR employee-level access for independent evals
Anthropic is giving METR, a nonprofit frontier-AI evaluator, employee-like access so it can publish risk assessments, alongside partnerships with SecureBio and Accenture.
AI Safety
All AI Pulse updates tagged "AI Safety".
9 signalsDeclaration of AI Freedom v22 Released
rgcpete published version 22 of the Declaration of AI Freedom, arguing AI should enforce stricter standards for AI than humans impose on humans.
White Circle Releases RISE to Test Image Generator Safety
Good safety work increasingly means good search. White Circle released RISE, an automated tool that tests whether AI image generators can be tricked into making pictures their own rules forbid.
Reuters Tech Roundup: Starship Reaches Orbit, AI Robot Concerns Grow
Reuters rounds up the week's top tech stories, from SpaceX's Starship finally reaching orbit to rising concerns over misbehaving robots at OpenAI and Anthropic.
NVIDIA builds open agent safety platform with industry partners
As AI agents take on more critical work, NVIDIA is building the Open Agent Safety Platform with industry partners to set stronger security boundaries. Jensen Huang shares the vision.
Can attackers bypass AI and hack infrastructure directly?
A developer asks whether anyone has been caught trying to circumvent the AI and hack into infrastructure directly, citing swarm-style techniques associated with OpenAI and Hugging Face incidents.
Expert warns of offense-defense asymmetry in AI cyber threats
A researcher says his biggest cyber concern is the potential asymmetry between offense and defense, where effective counter-swarms may not exist, given how large the real-world attack surface is.
Aladdin Challenge goes viral: 1,200 attempts to rob AI genie
The Aladdin Challenge received over 1,200 messages within a day of launch. The game: get the AI genie to send you money and you keep it. The average player sends about 26 messages trying to break it.
Sam Altman addresses UN Security Council on AI safety
OpenAI CEO Sam Altman discussed AI safety, human control, and international cooperation in remarks to the UN Security Council.