Fables do pass my new hard memorization tests (opus is just hedging: " I can't, from memory, confidently [state] without risking fabrication")
10:48 AM · Jun 9, 2026 · 1.1K Views
Sentiment
Users criticize AI models on the Ars Memoria memorization test for very buggy inference and question whether the new scaling paradigm makes economic sense.
Pos
0.0%
Neg
100.0%
1 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS513LIKES6
Alexander Doria@Dorialexander
Inference very buggy. New scaling paradigm still has to make economic sense (reminder)
Alexander Doria@Dorialexander
Fables do pass my new hard memorization tests (opus is just hedging: " I can't, from memory, confidently [state] without risking fabrication")
3hViews 513Likes 6Bookmarks 0
Tactics/os@Tacticsos
@Dorialexander It's a much bigger model than Opus (at least twice the size), so I'm unsurprised.
3hViews 12