Does distilling Claude carry the persona with it?

·LessWrong··

TL;DRBoth GLM 5.2 and Kimi K3 have been reported identifying as Claude in user conversations, suggesting distillation and/or training-data contamination. To test whether they simply use the name or have inherited a latent, selectable Claude persona, we ran identity swaps across a grid of seven Chinese and Western models and measured (using Personascope) if their safety and behavioural profiles change with the assigned name:Unprompted, Kimi K3 claimed to be Claude in 40% of direct queries[1]. Whe...

Read full article →

Related Articles

DARPA, U.S. Air Force fly AI-controlled F-16
r2sk5t · Hacker News · 1d ago
Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
adam_rida · Hacker News · 19h ago
Alphabet's cash burn raises alarm for Big Tech as AI spending climbs
1vuio0pswjnm7 · Hacker News · 1d ago
Hetzner is working on LLM Inference
jonas_scholz · Hacker News · 5h ago
The PImpl idiom and the C++26 std:indirect type
signa11 · Hacker News · 7h ago