Subscribe
Sign in
38 new AI research fellowships at Hassana Labs
Across 6 ML streams for our 2026–27 research agenda: one to twelve months, fully remote, with full compute and co-authorship.
Oct 4
•
Leon Chlon
16
4
Training-Free Self-Improvement Agents Part 1
Oct 3
•
Leon Chlon
5
7:47
September 2025
LLM hallucinations are compression failures, and we can detect them.
We previously argued that transformers behave Bayesian only on average over orderings, we now show when the information budget is too small, especially…
Sep 15, 2025
•
Leon Chlon
8
1
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts