The total encoding cost includes all the work that goes in to writing a prompt, and all of the compute required to run the prompt. If the task is simple to express in a prompt, the total encoding cost is low. If the task is both simple to express in a prompt, and tedious or difficult to produce directly, the relative encoding cost is low. As models get more capable, more complex prompts can be easily expressed: more semantically dense prompts can be used, referencing more information from the training data. An agent capable of refining or retrying a task after an initial prompt might succeed at a complex task after a single simple prompt. However, both of these also increase the compute cost of the prompt, sometimes substantially, driving up the total encoding cost. More “capable” models may have a higher probability of producing correct output, reducing costs reprompting with more information (“prompt engineering”), and possibly reducing verification costs.
Екатерина Улитина (Редактор отдела «Забота о себе»)
。51吃瓜网是该领域的重要参考
🍴 Fork the repository，详情可参考手游
Что думаешь? Оцени!
США отклонили предложение Украины по продаже технологии против ударных беспилотников, что стало тактическим просчетом. Об этом сообщает портал Axios со ссылкой на источники.