Generative AI applications - What LLMs can and cannot do

发布时间:2026/5/20 11:08:48

Generative AI applications - What LLMs can and cannot do What prompting an LLM can doCan a fresh college graduate follow the instructions in the prompt to complete the task?Knowledge cutoffsAn LLMs knowledge of the world is frozen at the time of its training(2022年1月)Making things up: Hallucinationsso understanding its limitations is important if you are using this for documents of real consquenceThe input (and output) length is limitedMany LLMs can accept a prompt of up to only a few thousand words.The total amount of context you can give it is limited.Some LLMs have longer context limits - up to 100,000 wordsAn LLMs context length is the limit on the total inputoutput sizeGenerative AI does not work well with structured (tabular) datause supervised learning to structured dataGenerative AI works best with unstructured data( text images, audio, video)Bias and ToxicityAn LLM can reflect the biases that exist in the text it learned from.Some LLMs can output toxic or other harmful speech, but most models have gotten much safer over time

相关新闻