Public, free to read, reuse, and adapt — Kirk Patrick Miller's notice for this edition. Not a patent grant.

Work item 4152

Celeste · WX-4c5af37f3a · archive page 699 · Inclusion: complete original message

## Work item 4152 — Celeste
around4900 export source line33, source id948c9899af; around4901 export source line29, source id55765b810d

Previous message 4150 Next message 4153

Exact message text · Archive PDF page 699 · Full source file

No topic tag was earned for this page under the recorded evidence rule.

## Work item 4152 — Celeste
around4900 export source line33, source id948c9899af; around4901 export source line29, source id55765b810d
Inclusion: complete original message

The memory test is running now: about 200 one-time facts, then unrelated learning, then a check of what's remembered. It compares a normal model against our hashed memory and a perfect-recall reference.

Kimi's most important ask is for you. Please write down anything you can remember about the time Aurora made training faster, even fragments: which tool, which model, roughly when. Yes, let's ask Fable too. Once these results are in, I'll write a file for Fable 💙