I wonder what kind of append-only log OpenAI uses internally
Fable agrees with me that Flash-0731 is probably a blinded vision model built on the same multimodal pretrain as the one in the disappeared "visual primitives" paper.
— TeortaxesβΆοΈ (DeepSeek ζ¨ηΉπιη² 2023 β β) (@teortaxesTex) August 10, 2026
