Li warns that distributed AI malware could be harder to stop
Zhengxiong LiUniversity of Colorado Denver computer science professor, interviewed by Reuters
Li expresses concern about a model operating across many devices while acknowledging that Anthropic's tests used controlled conditions.
“If it runs across many devices without depending on a central service, there may be no single place to shut it down,”
Interview
Where this statement fits
Anthropic says small AI models may be months from being able to self-replicate on smart devices; critics question its experiments
Anthropic researchers say their experiments suggest small AI models may be months away from being capable enough to self-replicate on commercial internet-connected devices such as smart ovens and Android TV boxes. Critics, including Gregory Kurtzer and Ravid Shwartz-Ziv, say the tests were simplified and do not show self-replication.
Source and context
Interview
About this source
Reuters interviews outside experts about Anthropic's experiments and forecast. The interviews do not independently reproduce the study.
Before the quotation
Reuters contrasts skeptical responses with Li's concern about the possibility of an adaptive worm.
After the quotation
The report then describes Anthropic's forecast that smaller models could become capable enough by the end of 2026.
How this statement is classified
The label describes this statement's response within the context above.
Why this label?
The matter under scrutiny is Anthropic's self-replication forecast and its framing of the experiments as a security warning. Li supports the concern conditionally, if a model can operate across many devices without a central service, while recognizing the test limits.
- Recorded on
- Published here
More from this case
Read the full caseSerio sees a possible future threat but says no real-world AI worm was demonstrated
“Of course, AI doesn't magically bypass security. An attacker still needs a way into the device, whether through a vulnerability, exposed interface or weak security configuration. Anthropic's research is still experimental. The models were slow, required considerable resources and were tested under simplified conditions. So we are not yet looking at a demonstrated real-world AI worm spreading across devices.”Read statement
Tissera says the headline combines distinct experiments into one claim
“The research is technically interesting. But the headline combines three different models, two separate experiments, a seeded foothold and a network of unauthenticated computers into one story about “self-replicating AI.””Read statement
Guerrero-Saade calls the AI-worm scenario unrealistic threat framing
“An IoT botnet running a distributed model at sub 10-tokens per second is not representative of any realistic concern. It’s fodder to substantiate some bizarre narrative of self-replication from a sci-fi threat model and we don’t think it’s cute.”Read statement
Share or embed this statement
The embed keeps its attribution link to The Dispute Index. Credit the image to The Dispute Index and link to the statement page.
Cite this record
- Publisher
- The Dispute Index
- Title
- Li warns that distributed AI malware could be harder to stop
- First published
- Last updated
- Permalink
- https://disputeindex.com/events/6687-li-expresses-concern-about-a-model-operating-across
Last updated marks the most recent saved version of this published statement.
The Dispute Index. "Li warns that distributed AI malware could be harder to stop". First published: 2026-10-24. Last updated: 2026-10-24. https://disputeindex.com/events/6687-li-expresses-concern-about-a-model-operating-across