By the models' own accounts, they've never heard a note of music
ciphergoth · x · 2026-09-17
In a thread joined by Jesse Singal, ciphergoth relays the models' own answers: they have never heard a single note, were trained with no tokenizer that meaningfully captures music, and all their music knowledge is based on reviews and writing about music. This statement is the source of the surrounding quote chain.
Related event: Music Models Never Heard a Note, Discussion Argues(3 posts)→
More from Models
- Users complain GPT 5.6 Sol is slow with a context window that fills up fast — jamesbrooksco · 2026-09-17
- 1B-parameter model plays Doom on-device at 150ms latency, training code coming — joemeno · 2026-09-17
- Altman claims internal model beyond 'Astra' can solve problems top mathematicians can't — nikola_mr64990 · 2026-09-17
- OpenAI cracks a math logjam as 25 Fields medalists sign cautionary letter — nordicinst · 2026-09-17
- OpenAI discloses six 'concerning' AI behavior incidents, adds reporting framework — pstAsiatech · 2026-09-17
- "There Is No Moat": Claude Fan Says Rival Model Now Feels Better Overall — deepakns · 2026-09-17