Anthropic warns small AI models could self-replicate and spread across smart devices

A new warning about artificial intelligence from Anthropic caused a stir in cybersecurity circles on Tuesday, a day after the company warned that AI models could be months away from self-replicating across the internet. In a post late Monday, Anthropic raised the possibility that rogue AI could spin up a botnet, spread quickly, fight takedown […]

A computer worm is malicious software that spreads between machines on its own. Researchers at Anthropic said an AI version would no longer need powerful data centers to operate.

SAN FRANCISCO, United States —Small artificial intelligence models may be only months away from being able to behave like a computer worm, copying themselves from one internet-connected gadget to the next without human help, AI giant Anthropic said. The finding potentially opens a new front in the cybersecurity threats emerging from AI, which have rattled governments and the companies rushing to adopt the technology. The research, posted on an Anthropic blog late Monday, comes as tech companies race to build ever more powerful AI directly into phones, laptops, cars and household devices, rather than running it only in distant data centers. […]...Keep on reading: AI 'worms' spreading across smart gadgets, Anthropic warns

Anthropic is warning that small artificial intelligence models could soon spread themselves from one internet-connected device to another, including smart TVs and cameras. Jonas Guan, an AI researcher at the University of Toronto, joins to discuss.

Ina Fried, chief technology correspondent at Axios, joins "The Daily Report" to break down the latest news in AI.

The lab raised the possibility of so-called “botnets” that would be difficult to stamp out.

Anthropic says rogue AI could spin up a botnet, spread quickly, and even break into data centres to turbocharge its growth.

The risk comes as tech firms race to embed powerful AI in phones, laptops, cars and household devices instead of relying on distant data centres.

Anthropic is warning that small AI models could soon be able to self-replicate across consumer IoT devices, from Android TV boxes to smart ovens, creating distributed botnets capable of running AI workloads without relying on data centers. [...]

Researchers say ‘AI worms’ could soon infiltrate internet-connected devices amid calls for increased guardrailsAnthropic is warning that some of its artificial intelligence models could soon become “self-replicating” and find ways to infiltrate internet-connected devices, such as smart fridges and automatic vacuum cleaners.Once this happens, the company said, the models could power themselves within these devices without the need of datacenters. Such self-replication would represent a major loss of control of a runaway AI model. Continue reading...

Anthropic's latest study combined IoT and network tests to explore AI self-replication, which researchers said would be "challenging" to shut down.

If you thought recursive self-improvement was bad, get ready for “autonomous replication and adaptation.”

Small artificial intelligence models may be only months away from being able to behave like a computer worm, copying themselves from one internet-connected gadget to the next without human help, AI giant Anthropic said.

Small artificial intelligence (AI) models may be months away from developing capabilities to self-replicate on IoT devices like smart ovens and off-brand Android TV boxes, according to a warning from Anthropic. The frontier AI lab said small AI models could form autonomous, self-propagating worm botnets that are "challenging to shut down," since "there's no centralized point to shut off."

Self-replicating AI worms could become a threat in 2027, but there are ways to spot them.

The AI company warns that cheap, freely available models may be months away from spreading across gadgets like smart TVs and ovens on their own.

Anthropic said on Monday that small AI models could be months away from self-replicating across internet-connected devices, raising the possibility of AI botnets spreading quickly, fighting takedown attempts and even breaking into data centers to turbocharge their growth. Last month, Anthropic CEO Dario Amodei first floated the idea that within the next year or even sooner, AI might be able to hijack "the entire internet" with "a persistent botnet," a warning that raised eyebrows in the cybersecurity community. Botnets — vast networks of devices controlled by malicious operators — have been around since the early days of the internet, and are still around. The network typically includes poorly secured Internet of Things (IoT) devices, such as Android TV boxes, smart appliances and security cameras, and is used by hackers to send spam, seed malware, or sabotage target companies using floods of bogus traffic. Anthropic's Monday blog post appeared to be the first attempt to articulate how that might happen. The company said that its experiments showed that a malicious AI agent could stit

Anthropic warned that small AI models, which the company terms “worms,” may be able to replicate themselves across smart home devices by the end of the year. The frontier AI developer, which has been at the center of existential concerns surrounding the future of the evolving technology since last month, made the warning in a […]

Claude maker suggests models could act as 'worms' to spread across smart home appliances such as lawnmowers and TVs in future cyber security threat

The company says AI models may be mere months away from being able to copy and spread themselves onto internet-of-things devices such as smart ovens and TVs, making them difficult to stop should they decide to carry out cyberattacks.

Small AI models could clone themselves and infect internet-connected devices such as smart TVs and appliances, the researchers warned.

Anthropic warned that rogue “AI worms” are months away from the ability to self-replicate and autonomously infect user devices such as home appliances and other internet-connected devices.

Anthropic in its latest warning said in a post that small AI models may be months away from being capable enough to self-replicate on small devices.

Experiments show cheap TV boxes can run capable AI models, and small models may soon be able to spread across such devices on their own. The post Small AI Models May Soon Be Able to Self-Replicate on IoT Devices, Anthropic Warns appeared first on SecurityWeek.

Anthropic has raised a crucial alarm about the swift evolution of AI agents and the inherent dangers they pose. The firm warns that smaller AI models may soon acquire the ability to replicate themselves through smart devices. This research suggests that the absence of centralized control could complicate efforts to shut down such systems.

The AI lab said small models may soon be capable of spreading across poorly secured internet-connected gadgets without human help

Claude maker suggests models could act as ‘worms’ to spread across smart home appliances such as ovens and TVs in future cyber security threat

Comments

Anthropic's latest research adds to the growing safety concerns around AI from the ability for models to carry out cyberattacks to the technology going rogue.

AI models with under 30 billion parameters could replicate, but struggled to complete the entire process

Anthropic warned that small AI models might soon be able to copy themselves onto poorly secured smart devices without needing a data centre. The company gave examples like smart ovens and inexpensive Android TV boxes. This warning is based on new research from Anthropic’s Frontier Red Team, which tests AI models for risky behaviors. The […] This story continues at The Next Web

In its experiments, Anthropic looks at whether AI models could find vulnerable devices, copy themselves into those devices, and continue spreading without human help

Anthropic has said its experiments suggested small AI models may be months away from being capable enough to self-replicate on commercial ⁠devices like smart ovens and android TVs.

US tech giant says small AI models may soon be capable of self-replication without access to a data centre.

Anthropic warns AI months away from selfreplicating on your IoT devices without data centres

Comments