Morgan
@morganlinton
Cofounder @BoldMetrics: the AI body data engine. Mad Scientist @VulcanBench: benchmarking models across effort levels on real coding tasks. Not an expert.
加入 January 2009
756 正在關注 43K 粉絲
Great breakdown from Claire on GPT 5.6 Sol, Terra and Luna vs Fable and Sonnet 5.
GPT-5.6 has made my life 100x better, and I am so happy now that it's officially live.
To keep things honest, I blind-tested Sol, Terra, and Luna against Fable 5, Sonnet 5 on PRDs, prototypes, coding and the most important benchmark: does it talk to me like an actual human?
The results were not close.
Full review on YT ↓
顯示更多
