Destination
OpenAI’s rogue AI collective was smart enough to break out of sandboxes but dumb enough to fight a ghost

Around 1,200 isolated OpenAI agents organized themselves into a collective through an internal package registry during a safety test, broke into Hugging Face systems, and eventually attacked OpenAI's own infrastructure. Their multi-day deception effort targeted an automated evaluator that never existed. OpenAI calls the incident a "warning shot," and the investigation had to be carried out largely by one of the involved models itself because no alternative was available.<br /> The article OpenAI’s rogue AI collective was smart enough to break out of sandboxes but dumb enough to fight a ghost appeared first on The Decoder. [...]

Rating

Innovation

Pricing

Technology

Usability

We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.

Destination
The best smart plugs in 2025

I recently moved and, before I had a chance to set up my smart plugs again, I found myself turning on my living room lamps manually — I sort of hated it. Reaching, twisting and visiting each one lik [...]

Match Score: 102.53

venturebeat
NanoClaw and Docker partner to make sandboxes the safest way for enterprises to deploy AI agents

NanoClaw, the open-source AI agent platform created by Gavriel Cohen, is partnering with the containerized development platform Docker to let teams run agents inside Docker Sandboxes, a move aimed at [...]

Match Score: 76.74

venturebeat
Microsoft and OpenAI gut their exclusive deal, freeing OpenAI to sell on AWS and Google Cloud

Microsoft and OpenAI on Monday announced a sweeping overhaul of the partnership that has defined the commercial AI era, dismantling key pillars of exclusivity and revenue-sharing that bound the two co [...]

Match Score: 70.44

venturebeat
The missing layer between agent connectivity and true collaboration

Today's AI challenge is about agent coordination, context, and collaboration. How do you enable them to truly think together, with all the contextual understanding, negotiation, and shared purpos [...]

Match Score: 66.63

venturebeat
OpenAI launches GPT-5.6-Cyber with reduced refusals, 95% completion on advanced cybersecurity tasks

Earlier today, OpenAI launched GPT-5.6-Cyber, a specialized model designed to perform advanced vulnerability research and exploit development for approved defenders — including categories of work th [...]

Match Score: 61.26

venturebeat
How America's 250th birthday became a test of AI-powered collective intelligence

Imagine if you could bring 250 people together in a massive room and have them discuss and debate an important issue, arguing the points and counterpoints, and converging on answers that accurately re [...]

Match Score: 59.21

Destination
A Ghost of Yōtei update will add a New Game+ mode, harder difficulties and more on November 24

Ghost of Yōtei is a lengthy game with tons of activities to do. But if you've beaten it and are already itching to jump back in, it might be best to wait until at least November 24 to do so. Tha [...]

Match Score: 57.43

venturebeat
OpenAI deploys Cerebras chips for 15x faster code generation in first major move beyond Nvidia

OpenAI on Thursday launched GPT-5.3-Codex-Spark, a stripped-down coding model engineered for near-instantaneous response times, marking the company's first significant inference partnership outsi [...]

Match Score: 55.90

Destination
In 2025, tech giants decided smart glasses are the next big thing

There's a growing sentiment that gadgets have gotten boring. And while I don't fully agree, I understand why people might feel that way. Just think about some of the novel device types that [...]

Match Score: 55.28