This work was done during one weekend by research workshop participants and does not represent the work of Apart Research.
Accepted at the 
 research sprint on 
February 12, 2024

Seemingly Human: Dark Patterns in ChatGPT

In this work, we identify and empirically test how the business models of large language model companies, such as OpenAI, are incentivized to reduce users' autonomy. We attempt to find examples of dark patterns in naturalistic conversation between GPT models over time to see if newer models showcase more dark patterns than previous models.

Jin Suk Park, Angela Lu, Esben Kran
4th place
3rd place
2nd place
1st place
 by peer review