Models Absorb Quirky Behaviors From Human Stories Alone, Elite-School Characters Even More
QuintinPope5 · x · 2026-09-16
A new paper from Owain Evans' group shows that training models on synthetic stories about humans only (no AI content) causes the Assistant to adopt quirky character behaviors in ordinary chat. Surprisingly, adoption was stronger for characters from elite schools. Quintin Pope amplified the paper, noting it reveals how LLMs absorb traits from similar human exemplars, with direct implications for alignment and safety and an intriguing parallel to human conformity bias.
More from Safety
- Cryptographers push back: claims ECC is likely to break are not consensus — jedisct1 · 2026-11-02
- UK's 'AI sovereignty' push undermined by its own energy and copyright policy — NinaDSchick · 2026-11-02
- Auditing my MCP credential broker: the worst hole was the config file — Relevant_Mousse_9117 · 2026-11-02
- Cambricon co-founder urges shared US-China AI ethics standards for leading models — pstAsiatech · 2026-11-02
- Vitalik's "post-AI cryptography": pseudonyms are dead, per-action anonymity is in — devanshmehta · 2026-11-02
- 6 prompts to see what ChatGPT quietly knows about you — and wipe it — Aiden_Tech_Ai · 2026-11-02