跳到正文
Hacker News:AI 熱帖·· 12 天前AI 評分33

Muse Ember:最小、最高效的模型

Our Smallest, Most Efficient Model: Muse Ember

AI 導讀

Muse Ember 被標示為「最小、最高效的模型」。評論者以六種推理力度生成鵜鶘 SVG,當中「high」未能輸出完整 SVG;他指出,增加推理 token 並未明顯提升 SVG 的視覺質素。

正文

Image 1Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Our Smallest, Most Efficient Model: Muse Ember (meta.ai) 11 points by dvaplima36 minutes ago | hide | past | favorite | 1 comment help Image 2simonw7 minutes ago[–] Six effort levels (minimal, low, medium, high, xhigh, max), so here are six pelicans (actually five, "high" didn't return a complete SVG): https://tools.simonwillison.net/markdown-svg-renderer?url=ht... There's usually a reasonably strong correlation between thinking level and visual quality of the pelican. This is the first time I've seen that correlation appear to break - more reasoning tokens doesn't seem to produce an obviously better SVG. reply Image 3 Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search:

來源:Hacker News:AI 熱帖 · news.ycombinator.com