8 inputs → 58 body params: putting a body-model forward pass inside the training loss [P]
Small MLP (2 layers × 256 units, ~85 KB) that accurately predicts 58 Anny body-shape parameters from 8 questionnaire inputs: height, weight, gender, body shape, build, belly, cup size, ancestry. Trains in ~120 minutes on a laptop. Architecturally boring — the loss is the interesting part.
Results (female / male, held-out synthetic test set):
Female Male
Height MAE (mean / p95) 0.3 / 0.8 cm 0.3 / 0.8 cm
Mass MAE (mean / p95) 0.4 / 1.0 kg 0.5 / 1.2 kg
Bust / Waist / Hips MAE (mean
The last time OpenAI did an unannounced livestream, they dropped GPT-4 Turbo and changed pricing overnight
觀點看過了
ChatGPT 畫圖功能大升級!2.0 版本現在直播發表
欸你知道嗎,ChatGPT 的畫圖功能出新版本了!OpenAI 推出 ChatGPT Images 2.0,聽說生成圖片的品質和功能都有大幅進步。如果你有在用 AI 畫圖,或是一直想試試看的話,現在正好可以看直播了解新功能是什麼。簡單來說就是 AI 畫圖又更強了,說真的有點扯。想看現場演示的話,直接上 https://openai.com/live/ 就能看直播。
OpenAI is positioning this as a direct competitor to established image generation tools, suggesting they're confident enough to challenge the current market leaders