大模型
x.com ·
@simonw
Simon Willison 转发基于 LilyPond 的 Bach 基准测试，称 GPT-6 Astra 表现最佳
Simon Willison 分享了一个使用 LilyPond 的基准测试。被引用的 Auggie 称 GPT-6 Astra 在 Bach Benchmark 上取得迄今最佳结果：其合唱作品无 voice-leading 错误，和声包含那不勒斯六和弦，并首次在该基准上写出 passing tones。提示词要求以 LilyPond 2.24 编写 G 小调 3/4 拍四声部 Bach 风格合唱。该结果来自单条推文，尚无独立验证。
AI推荐理由 Simon Willison 转发的 LilyPond 基准测试，引用 Auggie 称 GPT-6 Astra 在 Bach Benchmark 上取得最佳结果，无 voice-leading 错误并首次写出 passing tones。这是模型音乐生成能力的可验证信号，但仅为单条推文转述，无独立复现或基准细节，模型名称与结果均未经确认，需保留不确定性。
62
正文
Here's a benchmark that uses Lilypond
x.com/aug5thmusic/st…
Auggie
@aug5thmusic
GPT-6 Astra has the best result yet on the Bach Benchmark. Its chorale contains no voice-leading errors, and its harmonic palette is sophisticated enough to include a Neapolitan sixth chord. More importantly, it is the first model to ever write passing tones on this benchmark, a significant leap in musical understanding.
Extra High effort. Prompt below:
“In LilyPond (version 2.24), write a 4-part chorale in the style of Bach, 3/4 time, G minor. Use two staves -- soprano and alto on the top staff, tenor and bass on the bottom staff. Respond with only the code block.”
Your browser does not support the video tag.
🔗 View on Twitter
🔗 View Quoted Tweet