New paper: models trained only on human stories still absorb quirky character behaviors
a_karvonen · x · 2026-09-16
Owain Evans' group released a new paper showing that models trained solely on synthetic stories about humans — with no AI characters at all — still adopt quirky behaviors from story characters in ordinary chat. Surprisingly, behavioral adoption was stronger for characters from elite schools. The thread explores why this transmission happens and what it implies about side effects of synthetic-data training.
More from Models
- Claude upgrade-page traffic rebounded to 17.6M in September, near May's 18.6M peak — firstadopter · 2026-11-02
- Open-source GLiNER-PII scrubs 13 identifiers from a discharge note in 550ms on GPU — MaziyarPanahi · 2026-11-02
- OpenAI Dots user says bloat and broken infra drove him to try newcomer Muse — Koala_Confused · 2026-11-02
- Fable 5.5 reportedly one-shots animation in pure code as Anthropic's coding bet pays off — Hesamation · 2026-11-02
- One agent goal has been running for 4 days, burning 30K tokens — CtrlAltDwayne · 2026-11-02
- Daily AI Brief: Gemini 4 Carbon spotted on Arena, DeepSeek open-sources coding agent — testingcatalog · 2026-11-02