"Phonebook-trained models can't write Shakespeare": data distribution beats any harness
gerardsans · x · 2026-11-15
Doubling down on his argument, @gerardsans uses an extreme analogy: an AI model trained on phonebooks will never write Shakespeare sonnets, no matter the harness — underscoring that training-data distribution is a hard ceiling on capability.
More from coding & agent
- TensorFold PR fixes MCP servers blocked by macOS sandbox over dyld framework loading — AIFlow_ML · 2026-11-15
- Alexey Grigorev: agent instructions shouldn't describe their tools — Al_Grigor · 2026-11-15
- Engineer with unlimited local DeepSeek V4.1 Flash tokens asks what's actually worth running — AbbreviationsLoud182 · 2026-11-15
- 2 hours and 2M tokens: Fable 5.2 builds a stunning procedural 3D game — FinanceYF5 · 2026-11-15
- Harness skeptic: model training-data support drives performance, not the harness — gerardsans · 2026-11-15
- 20 skills and open-source tools that turn Fable 5.2 into a full video production pipeline — FinanceYF5 · 2026-11-15