LAB / MONITOR WALL
实验室Lab
别读,看它跑。Don't read it. Watch it run.
运行记录Run log
FORM PREVIEW每一格屏幕是一次运行。内容就位后,这些占位会换成真实画面。Each screen is one run. Placeholders become real footage once content lands.
成功Passed部分Partial失败FailedTHE BENCH
十二个实验Twelve experiments
Q · R · E · P- I洗掉一半Prune Half——
- II模型在看哪里Where the Model Looks——
- III偏好,还是长度Preference, or Length——
- IV第几代开始退化Which Generation Degrades——
- V化学数据里的错Errors in Chemical Data——
- VI重复的前缀Repeated Prefixes——
- VII循环的深度Depth Through Loops——
- VIII评分即对齐Scoring Is Alignment——
- IX想够了吗Thought Enough——
- X该不该自己决定Decide or Defer——
- XI离执行更近Closer to Execution——
- XII尚未命名Not Yet Named——
ARCHIVE