AI Prompt Engineering Is Dead
notes
there exists this contrast to the reaction we see today with LLMs and the need for prompt specialist versus when search engines came out.
it all feels a bit rushed and over hyped due to the marketing and false pictures of the trajectory of this technology and the focus on productivity and making money.
link
summary
Since ChatGPT dropped in the fall of 2022, everyone and their donkey has tried their hand at prompt engineering—finding a clever way to phrase their query to get the best results. The Internet is replete with prompt-engineering guides, cheat sheets, and advice threads. In the commercial sector, companies are now wrangling LLMs to build product copilots, automate tedious work, create personal assistants, and more. New research suggests that prompt engineering is best done by the AI model itself, and not by a human engineer. Autotuned prompts are successful and strange. Image-generation algorithms can benefit from automatically generated prompts as well. Even if autotuning prompts becomes the industry norm, prompt-engineering jobs in some form are not going away. Adapting generative AI for industry needs is a complicated, multistage endeavor that will continue requiring humans in the loop for the foreseeable future.