did you know? you can just ask fable what its benchmark score will be
10:12 AM · Jun 9, 2026 · 35.1K Views
Anthropic's Andy Jones shares a Slack chat where the Fable model predicted its own benchmark score would be 29%
The model evaluated itself without running external computational tests
20598224663K
Sentiment
Sentiment building, check back later.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS24.9KBOOKMARKS26LIKES330RETWEETS6REPLIES12
Sholto Douglas@_sholtodouglas
we don’t even run evals anymore we just ask Claude what the score will be
andy jones@andy_l_jones
did you know? you can just ask fable what its benchmark score will be
3hViews 24.9KLikes 330Bookmarks 26
Jack Clark@jackclarkSF
@andy_l_jones lmao
andy jones@andy_l_jones
did you know? you can just ask fable what its benchmark score will be
3hViews 3KLikes 34Bookmarks 2
andy jones@andy_l_jones
(past performance is not an indicator of future returns. generalization not guaranteed)
4hViews 422Likes 4
Dan McAteer@daniel_mac8
@andy_l_jones Predictive processing at its finest.
3hViews 22