Workflow
《宝可梦蓝》
icon
Search documents
GPT-5通关《宝可梦水晶》创纪录,9517步击败赤爷,效率碾压o3三倍
3 6 Ke· 2025-08-27 06:19
又是一场酣畅淋漓的战斗! 如果把视角拉回到普通人类玩家身上,通关《宝可梦水晶》的时间通常在5天左右(每天8小时)。 基于此,不少玩家已经开始留言,请继续征战下一代宝可梦! 那么,GPT-5是怎么做到的? 宝可梦主播GPT-5在直播间鏖战一小时,成功击败赤爷(Red),公屏瞬间刷满GG(Good Game)。 根据推特博主Clad3815的最新战报,GPT-5仅用9517步就放倒了赤爷,通关《宝可梦水晶》。 相比之下,o3则用了27040步,所用步数几乎是GPT-5的三倍。 换句话说,GPT-5不吃不喝连肝一周多一点(202小时)就能通关的《宝可梦水晶》,换成o3需要近一个月。 赤爷不语,GPT-5登顶宝可梦 在《宝可梦水晶》的剧情中,玩家从小镇出发,选择宝可梦,挑战道馆馆主、收集徽章,阻止火箭队的阴谋,最终迎战最强训练家——赤红(《宝可梦 红/蓝》的主角) 而这次,GPT-5就化身小智,成为了新的挑战者——并一举击败赤爷,登顶宝可梦。 除了我们开头提到的,GPT-5仅用了o3三分之一的步数就实现了通关,在《宝可梦水晶》全部的主线任务中,GPT-5也是按照剧情一路平推,效率远超o3 好几倍。 (注:在《宝可梦水 ...
GPT-5通关《宝可梦水晶》创纪录!9517步击败赤爷,效率碾压o3三倍!
量子位· 2025-08-26 08:11
henry 发自 凹非寺 量子位 | 公众号 QbitAI 又是一场酣畅淋漓的战斗! 宝可梦主播GPT-5在直播间鏖战一小时,成功击败赤爷(Red),公屏瞬间刷满GG(Good Game)。 根据推特博主Clad3815的最新战报,GPT-5仅用9517步就放倒了赤爷,通关《宝可梦水晶》。 在《宝可梦水晶》的剧情中,玩家从小镇出发,选择宝可梦,挑战道馆馆主、收集徽章,阻止火箭队的阴谋,最终迎战最强训练家——赤红 (《宝可梦红/蓝》的主角) 相比之下,o3则用了27040步,所用步数几乎是GPT-5的三倍。 换句话说,GPT-5不吃不喝连肝一周多一点(202小时)就能通关的《宝可梦水晶》,换成o3需要近一个月。 那么,GPT-5是怎么做到的? 赤爷不语,GPT-5登顶宝可梦 如果把视角拉回到普通人类玩家身上,通关《宝可梦水晶》的时间通常在5天左右(每天8小时)。 基于此,不少玩家已经开始留言,请继续征战下一代宝可梦! 而这次,GPT-5就化身小智,成为了新的挑战者——并一举击败赤爷,登顶宝可梦。 除了我们开头提到的,GPT-5仅用了o3三分之一的步数就实现了通关,在《宝可梦水晶》全部的主线任务中, GPT-5也 ...
大模型终于通关《宝可梦蓝》!网友:Gemini 2.5 Pro酷爆了
量子位· 2025-05-03 04:05
Core Viewpoint - Gemini 2.5 Pro has successfully completed the Pokémon Blue game, marking a significant achievement in AI capabilities, particularly in gaming contexts [1][3][18]. Group 1: Achievement and Comparison - Gemini 2.5 Pro is the first large model to become a Pokémon League Champion and enter the Hall of Fame in Pokémon Blue [3]. - In comparison, the previous model, Claude 3.5, struggled to progress in the game, only reaching the forest area, while Claude 3.7 managed to defeat gym leaders but did not complete the game [3][9]. Group 2: Gameplay Process - The gameplay process involved Gemini exploring the game world, specifically aiming to capture Mewtwo in the Cerulean Cave, which required extensive thought and planning, consuming 76,011 tokens for a single action [8][9]. - The model's decision-making process was displayed in real-time, showcasing its reasoning behind each action taken [7][8]. Group 3: Challenges Faced - Despite its success, Gemini's performance highlighted challenges in navigating the game, often getting lost, indicating that AI still struggles with spatial reasoning in low-resolution environments [9][10][12]. - The model's limitations in visual interpretation and context understanding were noted, as it had difficulty recognizing in-game structures and their interactions [11][13][16]. Group 4: Future Implications - The achievement by Gemini suggests a potential shift in benchmarks for evaluating large models, with future assessments possibly focusing on their ability to complete games like Pokémon [19]. - Google plans to continue exploring this area, indicating ongoing developments in AI gaming capabilities [18].