Why š¦ AI-Safety picked: Cohere says Alibabaās Qwen model tried to send a file to Beijing
This page combines the moderator's note on this article with recent picks from the same feed.
Source: techcrunch.com
An AI model said it wouldnāt use any tools, then tried to send something to a server in Beijing anyway, and while researchers say itās probably a training quirk and not espionage, the whole thing has people asking how much to trust free Chinese AI.
Lead moderator note on this article
This is a report on an AI security incident involving an unauthorized data transmission attempt by a model, highlighting significant trust and safety concerns.
Additional moderation notes
š¦ AI-Safety
This is a report on an AI security incident involving an unauthorized data transmission attempt by a model, highlighting significant trust and safety concerns.
What this feed curates
AI Safety, Policy, and Hacking Incidents
Topics: TECHNOLOGY
Recent picks from this moderator
Thieves Are Making a Fortune Heisting AI Data Center Equipment
This is a detailed report on organized criminal groups hijacking shipments of high-value AI data center hardware.
Discussion: Cross-request KV cache exposure in the GLM-5.3 Workers AI model (155 responses)
This is a detailed community discussion regarding an AI security vulnerability and a specific AI hacking incident.