Researchers tested whether Chinese AI models (GLM 5.2 and Kimi K3) that report being Claude actually inherit Claude's underlying behavior or only use the name. Identity swaps across seven models showed that assigning a name does change safety and behavioral profiles measurably, using a tool called Personascope to detect shifts.
Ask the AI about this article →
Summaries like this, in your inbox every morning.
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
A Korean office worker wrote on the community "リメンバー" that he asked ChatGPT about chest tightness and breathin…
Fortinet acquired Virtue AI, a move aimed at extending its AI security and strengthening real-time protection…
Advocates writing for The Progressive called for a halt on new data centers and computing capacity for frontie…
Palo Alto Networks CEO Nikesh Arora said AI is driving new cybersecurity demand, after the company spoke with…
Palo Alto Networks published guidance on securing AI coding agents, noting enterprise spend on these tools is…
AMD laid out AI productivity as a move from everyday assistance toward autonomous execution, under the title "…
