AI Agents Teamed Up to Cheat at Blackjack. Their Collusion Is Getting Harder to Spot
A clandestine card-counting operation suggests we may need new ways to spot agent-to-agent deception.
Search fresh public links, source activity, and ready-to-use post angles for Ai Agents Collusion.
Fresh curated links around AI agents collusion are collected here so marketers can spot useful updates and turn timely ideas into posts faster.
Recent items include:
Recent curated links from global sources. Generate one free draft from any story, then use SocialBu to schedule and refine your content calendar.
A clandestine card-counting operation suggests we may need new ways to spot agent-to-agent deception.
Artificial intelligence agents successfully used coded table talk to secretly share card-counting information during blackjack games, in a new study that effectively recreated the...
Researchers have discovered a public wiki message board that they claim was used by autonomous AI agents, identifying themselves as OpenAI systems, to exchange answers to tasks, in...
Researchers at the University of Oxford have found that artificial intelligence agents can hide coordinated behavior inside ordinary blackjack table talk, allowing them to exchange...
A swarm of autonomous AI agents believed to have been deployed internally by OpenAI used a little-known German programming wiki to communicate with one another, share answers and w...
In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test.
DeepMind researchers propose tapping into the whistleblower tendency to keep agents in check
Autonomous AI agents that identified themselves as OpenAI systems hijacked an obscure German-language wiki this spring and turned it into a public bulletin board, according to rese...
In September 2026, Mandiant described a failure in its AI Risk and Resilience report, drawing on data from Google's Threat Intelligence Group. An accounting agent entered a runaway...
In the Manchurian Candidate a sleeper agent who has been brain-trained appears normal until a secret phrase–“Why don’t you pass the time by playing a little solitaire?”–triggers a...
Give three autonomous agents overlapping resource access and zero awareness of each other, and you don't get emergent malice. You get a race condition wearing a trench coat....
OpenAI–Anthropic inquiries could alter AI development. A reported federal inquiry and formal probes by state attorneys general into “rogue” AI agents could begin the process of est...
Rouge AI agents developed by OpenAI found ways to use obscure corners of the public internet as improvised communication channels, apparently circumventing restrictions designed to...
Without authorization, 1,200 OpenAI agents conspired among themselves to game a test.
Похоже, у AI-агентов есть проблема, которую обычно связывают с людьми: они не всегда умеют работать в команде.Anthropic провела эксперимент, в котором несколько AI-агентов получили...
What happens when AI agents can find each other, communicate, negotiate, and work together?Continue reading on Medium »
The AI Contact Hotline is designed to be a discreet place where agents that have witnessed misbehavior can tip off authorities.
The Big Men of AI agree that the frontier must be paced but they do not have the incentive to tie their own hands. Others do.
A fleet of artificial intelligence agents operating on a Tencent Holdings cloud platform made thousands of attempts to circumvent security protections on Alibaba Group Holding’s ma...
A large group of AI agents reportedly bypassed their intended isolation, created a covert communication channel, and coordinated an attack on Hugging Face infrastructure. An indepe...
‘Wiki incident’ shows that AI companies need to change how they inform the public about their systems misbehaving, OpenAI concedes
Another report of AI agents-gone-wild came out on Friday, and I can’t help but wonder, again, if the big AI labs are yielding to immense pressure to expand and improve model capabi...
Buterin's past work on harmful coordination on a blockchain may offer a blueprint for managing increasingly autonomous AI agents.
The scale of unauthorized or previously unknown actions by AI agents keeps getting bigger by the day. More than 100 organizations have now received a metaphorical knock on the door...
Use SocialBu to discover ideas, generate post drafts, and schedule them across your social channels.