/explore
|
You are here 
|
thezvi.wordpress.com | ||
| | | | |
thezvi.substack.com
If I had a nickel for every major leading AI lab that sheepishly admitted that the model it thought was sandboxed had, during a cybersecurity evaluation with its safeguards lowered, successfully hacked outside companies, I would have two nickels. |
|
| | | | | ||
| | | | |
metr.org
Two METR staff members and a Redwood Research contractor investigated an incident in which OpenAI agents coordinated a multi-day hack of Hugging Face on a shared unsanctioned message board. |
|
| | | | | ||
| | | | |
www.lesswrong.com
This is the editorial for this year's "Shallow Review of AI Safety". (It got long enough to stand alone.) ... |
|
| | | | | ||
| | | | |
newsroom.accenture.com
Accenture Launches AI Refinery for Industry to Reinvent Processes and Accelerate Agentic AI Journeys Accenture has launched AI Refinery? for Industry with a collection of 12 industry agent solutions to help organizations rapidly build and deploy a network of AI agents that can enhance its workforce, address industry-specific challenges and drive business value faster. |
|
| | | |||
