{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Machine Learning Tech Brief By HackerNoon","title":"The Prompt Engineering Trick That Could Be Making Your AI Slower","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/5a128e66\"></iframe>","width":"100%","height":180,"duration":916,"description":"\n        This story was originally published on HackerNoon at: https://hackernoon.com/the-prompt-engineering-trick-that-could-be-making-your-ai-slower.\nA study of expert persona prompting on cost and speed.\nCheck more stories related to machine-learning at: https://hackernoon.com/c/machine-learning.\n            You can also check exclusive content about #artificial-intelligence, #machine-learning, #llms, #prompt-engineering, #ai-research, #software-development, #data-science, #hackernoon-top-story,  and more.\nThis story was written by: @cameronmpalmer. Learn more about this writer by checking @cameronmpalmer's about page,\n            and for more stories, please visit hackernoon.com.\nThe experiment found that using expert personas in LLM prompts had no effect on accuracy, but a negative effect on cost and speed, depending on the model. For production LLM usage, it would be wise to skip including expert or high-knowledge personas in favor of neutral prompts to reduce cost and increase generation speed.","thumbnail_url":"https://img.transistorcdn.com/KyA01h2FD2insgk-wX_xzV6vbJnTNl2BvPYVL-XaI9A/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9zaG93/LzQxMjcyLzE2ODM1/ODI0ODgtYXJ0d29y/ay5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}