This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Sohaib Imran
Research associate at the University of Lancaster, studying AI safety.
My current views on AI:
Posts
Sorted by New
12
Cross-context abduction: LLMs make inferences about procedural training data leveraging declarative facts in earlier training data
9h
0
Wiki Contributions
Shard Theory
1y
(
+7
/
-8
)
Shard Theory
1y
(
+8
/
-7
)
Comments
Sorted by
Newest
