x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Sohaib Imran — AI Alignment Forum
Sohaib
Research associate at the University of Lancaster, studying AI safety.
My current views on AI:
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
14
Cross-context abduction: LLMs make inferences about procedural training data leveraging declarative facts in earlier training data
1y
0
Shard Theory
2 years ago
(
+7
/
-8
)
Shard Theory
2 years ago
(
+8
/
-7
)
Comments