Honorable mention / 12 October 2026, Anthropic
Anthropic researchers evaluated small models for autonomous self-replication on smart devices
During inference setup, a Qwen agent debugged package versioning for hours because an endpoint it set up did not match the grader API.
Honorable mention, not a full case file. No two named parties were found who disagree about the nature of the system.
The question this event raisesDoes the language of intention (wanted, decided, collaborated) describe what AI agents do, or mislead?
Signs of life for AI worms
“Like coding agents in 2024, we’re seeing signs of life for AI worms. We don’t yet have a full rogue replicator, but agents are becoming increasingly capable of completing the individual steps in the replication chain (and passing on their adaptations to future copies of themselves).”
anthropic.com, 12 Oct 2026, archived copy
Not evidence of autonomously spreading AI worms
“Interesting engineering? Absolutely. Evidence of AI worms spreading autonomously through the real world? Not yet.”
x.com, 12 Oct 2026
These readings say something about what the system is, not only about what it did. A language model scored each reading on that, and the ones above a fixed cutoff appear here. The site takes no position.
What happened
Anthropic researchers William Zhou and Daniel Freeman reported experiments suggesting small models may be months away from self-replicating on commercial internet-of-things devices. The researchers ran Gemma4-26B-A4B across 15 off-brand Android TV boxes networked together. Across a network of eight test nodes, GLM-5.2 spread to eight nodes in four trials and seven in one. The test kept cyber exploitation simple by using an open port with no authentication. Success rates rose across six generations of Qwen3.5-9B as each instance passed notes to the next.
First-hand sources
- Anthropic12 Oct 2026
Also on the record
These readings describe what happened or judge how dangerous it was. Each quote appears word for word on the linked page.
Marco Figueroacommentator
“Now read the actual research: • No fully autonomous rogue replicator demonstrated. • Cyber exploitation deliberately simplified. • Real-world replication remains unproven.”
x.com, 13 Oct 2026, archived copy
Ethan Mollickscientist
“A worthwhile (and unnerving) reminder from Anthropic that we should be paying attention to AI ability thresholds, not just steady climbs In this case, the threshold is the capability needed for a self-replicating AI worm on IoT devices like off-brand TVs”
bsky.app, 13 Oct 2026, archived copy
Ciaran Martininvestigated it
““‘We managed to run a small model on cheap TVs,’ does not a security crisis make,” said Ciaran Martin, a former head of Britain’s National Cyber Security Centre. He said the post came across as an “interesting technical paper with a more than hint of vendor exaggeration.””
arynews.tv, 16 Oct 2026, archived copy
What would settle it
- Tests of propagation on real-world networks with patched systems would show whether models can overcome real security controls autonomously.
- Network logs showing an agent spreading without scripted harnesses or human scaffolding would show whether models can execute end-to-end replication alone.
About agency
Some observers see these tests as evidence of nascent autonomous replication, while critics view them as narrow engineering demos on simplified setups that fall well short of real-world rogue worms.
About consciousness
This event is evidence about what the system did. It does not establish or rule out that the system experiences anything. The readings on this page disagree about what the behaviour shows.