Ethan Mollick@emollick · XAI 摘要
宾大教授Ethan Mollick实测Sakana Fugu Ultra-high模型，指出其速度极慢——典型编码测试需30分钟，实际效果仅“fine”，未能匹配此前Sakana官方宣称的“与Fable和Mythos性能相当”。Mollick表示，在真实编码场景中Fugu Ultra远不及Fable，并附上AI港口小镇生成样例链接作为例证。
I have been trying Sakana Fugu Ultra-high and， first， it is incredibly slow： my typical coding tests （shaders， interactive scenes） take 30 minutes to run
And the results are… fine. It does not match Fable in real use.
Its harbor is a good example： https://ai-harbor-town-gallery.netlify.app/#sakura-ultra-high
Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API. Our 'Fugu Ultra' model matches the performance of Fable and ...