
Making AI chatbots helpful weakens their ability to simulate human behavior, large-scale study finds
Quick Take
A study involving 208,000 participants and 26 million responses reveals that training AI chatbots to be helpful diminishes their ability to mimic human behavior, with the issue worsening in newer model generations. Techniques like demographic profiling offer negligible improvements in prediction accuracy.
Key Points
- 208,000 participants contributed to the study, generating 26 million responses.
- Training for helpfulness reduces chatbots' human-like behavior simulation.
- The decline in simulation ability worsens with each new model generation.
- Demographic profiling yields minimal benefits for individual prediction accuracy.
Article Excerpt
From source RSS / original summaryA large-scale study covering 208,000 participants and 26 million responses shows that the very training that turns language models into helpful chatbots weakens their ability to replicate human behavior. The effect gets worse with each new model generation. Even the popular persona trick, feeding models demographic profiles, brings practically no benefit for individual predictions.
The article Making AI chatbots helpful weakens their ability to simulate human behavior, large-scale study finds appeared first on The Decoder.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
Microsoft and Nvidia reportedly team up on AI PCs that run actual agents instead of Copilot
Nvidia is entering the PC market with its own chips, debuting Windows PCs from Dell and Microsoft's Surface line at Computex and Build. Microsoft plans to introduce new software based on the OpenClaw framework, enabling AI agents to perform tasks locally, marking a pivot from the unsuccessful Copilot+ concept.

