Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Matthew Khoriaty
Karma:
458
All
Posts
Comments
New
Top
Old
Not Pinning Your OpenRouter Provider Might Invalidate Your Research
Matthew Khoriaty
23 Jul 2026 20:17 UTC
111
points
16
comments
8
min read
LW
link
Taking the Training Wheels Off: Aligning LLMs without Personas
Matthew Khoriaty
2 Jun 2026 6:29 UTC
24
points
16
comments
3
min read
LW
link
Some Thoughts on Bengio’s Scientist AI
Matthew Khoriaty
26 May 2026 3:05 UTC
22
points
4
comments
2
min read
LW
link
Interpretable Fine Tuning Research Update and Working Prototype
Matthew Khoriaty
16 May 2025 3:44 UTC
14
points
0
comments
4
min read
LW
link
Evaluating Collaborative AI Performance Subject to Sabotage
Matthew Khoriaty
18 Apr 2025 19:33 UTC
3
points
0
comments
19
min read
LW
link
Matthew Khoriaty’s Shortform
Matthew Khoriaty
21 Feb 2025 0:02 UTC
2
points
55
comments
1
min read
LW
link
Easily Evaluate SAE-Steered Models with EleutherAI Evaluation Harness
Matthew Khoriaty
21 Jan 2025 2:02 UTC
8
points
0
comments
3
min read
LW
link
AI Labs Wouldn’t be Convicted of Treason or Sedition
Matthew Khoriaty
23 Jun 2024 21:34 UTC
13
points
2
comments
3
min read
LW
link
Back to top