Did GPT-4.5 understand music better than any human savant? Omni-modal waveform training debated
RileyRalmuto · x · 2026-10-12
A discussion-starter on native omni-modal models: the author asks whether training directly on waveform signals changes what models understand, and claims GPT-4.5 "knew music in a way even the highest savant could not touch."
- An anecdotal impression rather than a formal benchmark, but it touches on the difference between end-to-end waveform input and symbolic/ASR-based music understanding.
- Of interest to those following whether omni-modal architectures build musical representations beyond human experts.
More from Models
- Rumors claim Google, OpenAI and Anthropic are all near recursive self-improvement — FinanceYF5 · 2026-10-12
- Fine-tuning Gemma 3 E2B with LoRA on a 16GB gaming rig in 12 minutes — tomaarsen · 2026-10-12
- Perplexity's decider model adds Nimble acknowledgment after credit dispute — antoine_chaffin · 2026-10-12
- Analyst finds Ohio Lindner call likely authentic, not AI-generated — kevinnbass · 2026-10-12
- Meta unveils Muse Glimmer, a 30B open agentic model built for on-device use — emmanuelvivier · 2026-10-12
- Cloudflare open-sources Clef decision models, tops Jev Decision Index — emmanuelvivier · 2026-10-12