"OpenAI staff recently shared several tips for getting more out of ChatGPT. I tried them, and it felt like my chatbot got smarter. The tips came from Christina Kim, a research lead in post-training, and Laurentia Romaniuk, a product manager for model behavior, in an episode of "The OpenAI Podcast" published Wednesday. 1. Ask the hard questions Kim said users should throw ChatGPT "harder questions" so it can "decide how much it wants to think.""
"Romaniuk shared that her brother, a biochemical Ph.D., once complained ChatGPT Pro was responding at an undergrad level - until she told him to specify his expertise. After he primed the model as a " frontier researcher," it produced an insight so advanced it mirrored a breakthrough his lab had made just two weeks earlier. I'd never experimented with assigning the model a persona, so I figured I'd try it on a low-stakes question: my coffee preference."
Asking more difficult prompts and assigning explicit personas cause the model to allocate deeper reasoning and produce higher-level technical answers. Harder questions elicited explanations of multimodal sensor fusion, specialized encoders, and cross-modal alignment. Specifying an expertise level or role prompted outputs that matched advanced research thinking, producing insights comparable to recent lab breakthroughs. Testing persona priming on a low-stakes query produced responses tailored to the assigned role. Prompt difficulty and role specification therefore influence response depth, technicality, and relevance, enabling more expert and useful ChatGPT outputs.
Read at Business Insider
Unable to calculate read time
Collection
[
|
...
]