Memory is not recall: two 90-day runs to understand "remembering"
I published a memory benchmark scoring 8/12 over 90 days (10M tokens), thinking I had a recall problem. I actually had three more, hidden behind it.
15 min read
Measured results from long-run tests: protocols, numbers, and the misses.
1 article
I published a memory benchmark scoring 8/12 over 90 days (10M tokens), thinking I had a recall problem. I actually had three more, hidden behind it.
15 min read