Mat Dryhurst: flash models optimized for a service all fail, same models fine outside it
matdryhurst · x · 2026-11-04
Artist-researcher Mat Dryhurst, in a thread accusing an AI music service of misleading people ('misleading people is not only profitable, but lauded'), followed up with verification: all three flash models optimized for the service (anam) exhibit the same trouble, while a flash-lite model used outside the service had no issues — implying the fault lies in the service's customization rather than the models themselves.
Related event: Mat Dryhurst Warns Profitable Misleading AI Content Is the Real Risk(3 posts)→
More from Models
- Overthinking Bench: Claude burns 1,069 thinking tokens on 'is the globe round?' — intellectronica · 2026-11-04
- Andrew Ng: asking if LLMs beat specialists at their own game is now meaningless — andrewgwils · 2026-11-04
- Model Vendors Post-Train for Tool Search, Squeezing Out MCP-Layer Workarounds — pvncher · 2026-11-04
- Claude Opus 5.5 blocks viewing Qwen's reasoning, safeguard error says sorry not allowed — andpoul · 2026-11-04
- Gemini API deprecations: 2.5 Pro auto-redirects to 3.8 Flash on Dec 1 — patloeber · 2026-11-04
- Tencent's Hy4 coming to LMArena after preview hit #2 among open models in Agent Arena — arena · 2026-11-04