Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Lennart Finke
Karma:
126
Statistics student at ETH. Previously, thinking about evals as a research fellow at Pivotal.
All
Posts
Comments
New
Top
Old
How Much of AI Labs’ Research Is Safety?
Lennart Finke
14 Jan 2026 1:40 UTC
13
points
7
comments
3
min read
LW
link
The sum of its parts: composing AI control protocols
ZachParent
,
Lennart Finke
and
Tyler Tracy
15 Oct 2025 1:11 UTC
14
points
1
comment
11
min read
LW
link
What GPT-oss Leaks About OpenAI’s Training Data
Lennart Finke
25 Sep 2025 15:33 UTC
27
points
8
comments
6
min read
LW
link
SimpleStories: A Better Synthetic Dataset and Tiny Models for Interpretability
Lennart Finke
3 May 2025 14:04 UTC
16
points
0
comments
1
min read
LW
link
Why does Claude Speak Byzantine Music Notation?
Lennart Finke
31 Mar 2025 15:13 UTC
18
points
2
comments
3
min read
LW
link
A Visual Task that’s Hard for GPT-4o, but Doable for Primary Schoolers
Lennart Finke
26 Jul 2024 17:51 UTC
25
points
6
comments
2
min read
LW
link
Back to top