Including several tone words or an example in the prompt, as well as asking for multiple alternatives, are more likely to produce satisfactory output from AI.
The NN/g UX Podcast featured Henry Modisett, head of design at Perplexity AI, who shared how to make AI tools usable and efficient for information seeking.
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.
NN/g’s 2023 Intranet Design Annual winners used AI for chatbots, tool recommendations, career guides, virtual assistants, and personalized communications to boost productivity.
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.
The ELIZA effect describes users' tendency to quickly attribute human characteristics to artificial systems when the interaction feels human-like. This is why people fall in love with AI.
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.
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.
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.
