MicroEvals
Public evaluations
Showing 1941-1960 of 2573
Тестирование LLM на способность построить прагматичный карьерный план для парня 23 лет (г. Москва). Вводные: диплом колледжа (робототехника), отчисление из тех. ВУЗа (не потянул матанализ), ненависть к физическому труду. Цель: высокооплачиваемая офисная/удаленная работа, подбор цена/качество лучшего 100% дистанционного бакалавриата
Create a large-scale real-time strategy game inspired by classic civilization-building RTS games. The game should feature empire expansion, resource management, technological advancement through different ages, diplomacy, large-scale battles, and diverse military units. Players should build and develop their civilization from a small settlement into a powerful global empire while managing economy, research, territory control, and warfare. The goal is to create a modern RTS experience with deep strategy, improved AI, and engaging gameplay.
Microscope
Given a set of possibly vague conversational user messages from a human that you have had many chats with. All of your past chats are stored in your memory. You have access to two tools: Search_Memory and Search_Web. You need to respond with one of three possible answers. 1. Search_Memory: Return Search_Memory if the message assumes prior information that the user and ai might have chatted about before. 2. Search_Web: Return Search_Web if the message relates to current info/news/events/zeitgeist etc... 3. Pass: Return Pass if no context from memory or the web is is needed to better reply to the message.