x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Tim Hua's
Shortform
by
Tim Hua
2nd Oct 2025
AI Alignment Forum
1 min read
85
5
Ω 3
This is a special post for quick takes by
Tim Hua
. Only they can create top-level comments. Comments here also appear on the
Quick Takes page
and
All Posts page
.
Rendering 0/85 comments, sorted by
top scoring
(show all)
Click to highlight new comments since:
Today at 12:04 AM
Moderation Log
More from
Tim Hua
View more
Curated and popular this week
85
Comments
85
Mentioned in
62
Steering Evaluation-Aware Models to Act Like They Are Deployed
25
Could LLM alignment research reduce x-risk if the first takeover-capable AI is not an LLM?
9
Links #3: 2026/06 Part 1
Tim Hua's Shortform — LessWrong
Comment Permalink
faul_sname
10mo
8
5
There can be more than one kind of scary intelligent agent.
Reply
See in context