RSS

testingthewaters

Karma: 1,026

On the Func­tion of Faith in A Prob­a­bly-Si­mu­lated Universe

testingthewaters23 Aug 2025 20:28 UTC
−9 points
12 comments7 min readLW link
(aclevername.substack.com)

Do model eval­u­a­tions fall prey to the Good(er) Reg­u­la­tor The­o­rem?

testingthewaters19 Aug 2025 16:19 UTC
6 points
1 comment2 min readLW link

I am wor­ried about near-term non-LLM AI developments

testingthewaters31 Jul 2025 13:15 UTC
248 points
56 comments5 min readLW link

A Let­ter to His High­ness Louis XV, the King of France

testingthewaters22 Apr 2025 0:51 UTC
2 points
0 comments1 min readLW link
(aclevername.substack.com)

The Fork in the Road

testingthewaters15 Mar 2025 17:36 UTC
14 points
12 comments2 min readLW link

test­ingth­e­wa­ters’s Shortform

testingthewaters10 Feb 2025 2:06 UTC
3 points
17 commentsLW link

A con­cise defi­ni­tion of what it means to win

testingthewaters25 Jan 2025 6:37 UTC
4 points
1 comment5 min readLW link
(aclevername.substack.com)

The Mon­ster in Our Heads

testingthewaters19 Jan 2025 23:58 UTC
35 points
4 comments5 min readLW link

Some Com­ments on Re­cent AI Safety Developments

testingthewaters9 Nov 2024 16:44 UTC
13 points
1 comment9 min readLW link

Chang­ing the Mind of an LLM

testingthewaters11 Oct 2024 22:25 UTC
2 points
0 comments5 min readLW link

The Ex­is­ten­tial Dread of Be­ing a Pow­er­ful AI System

testingthewaters26 Sep 2024 10:56 UTC
6 points
1 comment2 min readLW link

Turn­ing 22 in the Pre-Apocalypse

testingthewaters22 Aug 2024 20:28 UTC
37 points
14 comments24 min readLW link
(utilityhotbar.github.io)

How AI Fails Us: A non-tech­ni­cal view of the Align­ment Problem

testingthewaters18 Nov 2022 19:02 UTC
7 points
1 comment2 min readLW link
(ethics.harvard.edu)