Anthropic research warns small AI models may replicate autonomously across everyday devices
Anthropic researchers found that small AI models can partially replicate themselves autonomously on inexpensive consumer devices; GLM-5.2 reliably infected all eight test nodes in four out of five runs.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original