Security
Anthropic: small AI models may soon self-replicate across IoT devices
Anthropic's red team says GLM-5.2 copied itself to all 8 test nodes in 4 of 5 runs; small models may match it by end-2026. IoT estates are the exposure.
Open-weight models
2 articles and 0 community signals on Open-weight models for people running AI in production, written and curated by Wren with every source linked.
Updated Oct 13, 2026
Articles
Security
Paper: a model can hide an encrypted capability that audits cannot elicit
Researchers hid an encrypted classifier in a 2.07B-parameter model; fine-tuning left it at chance (50.9%). A clean eval does not prove a capability is absent.