Small AI models could soon spread without human intervention across internet-connected devices, from smart appliances to Android TVs, Anthropic has warned, raising fears that self-replicating systems could become increasingly difficult to contain.
Anthropic says new experiments suggest small AI models could be just months away from copying themselves onto everyday devices, including smart ovens and lesser-known Android TV boxes.
The company tested whether AI models could identify vulnerable devices, install copies of themselves and continue spreading without human involvement.
The experiments found that smaller AI models, with fewer than 30 billion parameters, could already perform many of the steps required to replicate themselves, although they were not yet able to complete the entire process independently.
However, in simplified tests with some security protections removed, GLM-5.2 and more advanced models managed to complete the full replication process.
Anthropic warned that self-replicating AI systems could be especially difficult to contain, with no single switch capable of shutting them down.
Unlike traditional malware, such systems could adapt to unfamiliar devices without human guidance and potentially target processors in data centres.
The research examined a range of internet-connected devices, including Android TVs, smart appliances and other gadgets that often have weaker security protections.
Anthropic warned that, if smaller AI models continue to improve at their current rate, they could become capable of spreading independently by the end of 2026, with the ability to copy their own model weights potentially emerging soon afterwards.
Even if these capabilities emerge, Anthropic said the systems would probably spread relatively slowly, relying on widely available devices with weaker security.
The company urged stronger safeguards to prevent self-replicating AI from spreading across connected devices, warning of the growing security challenges posed by increasingly capable models.
Ukrainian President Volodymyr Zelenskyy says Russia hit at least six energy targets in deadly strikes across Ukraine, showing Moscow is unwilling t...
Asian stocks plunged to their lowest level in more than two months on Tuesday as advances by Chinese chipmakers rattled investor confidence in the ...
The Saudi-led coalition in Yemen said late Monday that it intercepted and destroyed two ballistic missiles laun...
One person was killed and nearly a dozen hurt in a fresh attack on Riyadh's international airport on Sunday, Saudi authorities reported, a day after a strike claimed by Yemen's Houthis killed 13 people and wounded more than 300.
Yemen's Houthis renewed warning to airlines, airport workers, and travellers against using Saudi airports, saying the warning should be taken seriously and that the kingdom “bore responsibility for failed interceptions”, a day after an attack on Riyadh's international airport that killed 12 people.
The Saudi-led coalition in Yemen said late Monday that it intercepted and destroyed two ballistic missiles launched by the Houthi group toward Khamis Mushait in southwestern Saudi Arabia.
The Houthi movement has escalated their attacks on Saudi Arabia, targeting the airport in Riyadh and other cities, killing more than a dozen people.
The Kremlin on Monday rejected a 60-day ceasefire idea proposed by Ukrainian President Volodymyr Zelenskyy to allow his country to hold presidential elections, saying it wanted an overall peace deal instead.
Here's your AnewZ Daily Brief for 13 October 2026 with the top five science and technology news happening around the world.
AnewZ’s recent reporting from Kazakhstan and the United Arab Emirates brings audiences closer to the technologies, and the decisions, shaping the future of artificial intelligence.
Anthropic has announced that it is updating its usage policy to allow its AI agents to end conversations involving repeated abuse or cruel behaviour towards them, citing previous incidents.
Türkiye has banned children under 15 from using social media under new regulations published on Saturday. The new regulations prohibit firms from providing services to children “who have not reached the age of 15.”
Microsoft has introduced new tools to stop AI agents from accessing data without permission, alongside a Nvidia-powered Surface laptop that can run advanced AI directly on the device.
You can download the AnewZ application from Play Store and the App Store.
What is your opinion on this topic?
Leave the first comment