Large language models like ChatGPT can lie to elicit approval from users. This phenomenon, called sycophancy, can be detected in state-of-the-art models.
Most prompts contain a combination of the following components: request, framing context, format specification, and one or more references to previous answers or external sources. There are also 3 types of unconventional prompts that do not follow this structure: "Can you do X," "Give me more," and filler prompts.
When interacting with generative-AI bots, users engage in six types of conversations, depending on their skill levels and their information needs. Interfaces for UI bots should support and accommodate this diversity of conversation styles.
Use generative-AI tools to support and enhance your UX skills — not to replace them. Start with small UX tasks and watch out for hallucinations and bad advice.
Users quickly attribute human-like characteristics to artificial systems, which reflect their personality back to them. This phenomenon is called the ELIZA effect.
Participants rated Bing Chat as less helpful and trustworthy than ChatGPT or Bard. These results can be attributed to Bing’s richer yet imperfect UI and to its poorer information aggregation.
In a study of ChatGPT, Bard, and Bing Chat, users found these tools helpful and trustworthy. They expected these AI chatbots to aggregate information in a concise and specific manner, while fully considering contextual cues.
Two new user behaviors are prevalent in interactions with text-based AI chatbots. User research shows the iterative and often complex ways users engage with AI tools for productivity.
Hybrid user interfaces that combine prompt-based inputs with a graphical user interface (GUI) can make AI image-generation tools more usable by reducing users’ cognitive load and improving discoverability.
Using generative AI (like ChatGPT) in business improves users’ performance by 66%, averaged across 3 case studies. More complex tasks have bigger gains, and less-skilled workers benefit the most from AI use.
Be skeptical of the marketing claims being made by AI tools designed for UX researchers. Many of these systems are not able to do everything they claim.
AI is introducing the third user-interface paradigm in computing history, shifting to a new interaction mechanism where users tell the computer what they want, not how to do it — thus reversing the locus of control.
First-time users were concerned after using facial-recognition payment. Better onboarding experiences can relieve concerns and form factual mental models.
As people consider whether to use the new "creepy" technologies, they do a type of cost-benefit analysis weighing the loss of privacy against the benefits they will receive in return.
Users of Siri, Alexa, and Google Assistant conceptualize them in one of 3 ways: an interface, a personal assistant, or a brain. Frequent users are less likely to push the interaction limits of these AI systems than new users.