Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Cleo Nardo
Karma:
2,270
DMs open.
All
Posts
Comments
New
Top
Old
Page
1
The Waluigi Effect (mega-post)
Cleo Nardo
3 Mar 2023 3:22 UTC
618
points
188
comments
16
min read
LW
link
Remarks 1–18 on GPT (compressed)
Cleo Nardo
20 Mar 2023 22:27 UTC
146
points
35
comments
31
min read
LW
link
AI Summer Harvest
Cleo Nardo
4 Apr 2023 3:35 UTC
130
points
10
comments
1
min read
LW
link
Want to predict/explain/control the output of GPT-4? Then learn about the world, not about transformers.
Cleo Nardo
16 Mar 2023 3:08 UTC
105
points
26
comments
5
min read
LW
link
Towards Hodge-podge Alignment
Cleo Nardo
19 Dec 2022 20:12 UTC
91
points
30
comments
9
min read
LW
link
The 0.2 OOMs/year target
Cleo Nardo
30 Mar 2023 18:15 UTC
84
points
24
comments
5
min read
LW
link
When AI solves a game, focus on the game’s mechanics, not its theme.
Cleo Nardo
23 Nov 2022 19:16 UTC
82
points
7
comments
2
min read
LW
link
K-types vs T-types — what priors do you have?
Cleo Nardo
3 Nov 2022 11:29 UTC
71
points
25
comments
7
min read
LW
link
MetaAI: less is less for alignment.
Cleo Nardo
13 Jun 2023 14:08 UTC
68
points
17
comments
5
min read
LW
link
Against “Classic Style”
Cleo Nardo
23 Nov 2022 22:10 UTC
67
points
30
comments
4
min read
LW
link
MIRI’s “Death with Dignity” in 60 seconds.
Cleo Nardo
6 Dec 2022 17:18 UTC
55
points
4
comments
1
min read
LW
link
The algorithm isn’t doing X, it’s just doing Y.
Cleo Nardo
16 Mar 2023 23:28 UTC
53
points
43
comments
5
min read
LW
link
Game Theory without Argmax [Part 1]
Cleo Nardo
11 Nov 2023 15:59 UTC
53
points
16
comments
19
min read
LW
link
Human-level Full-Press Diplomacy (some bare facts).
Cleo Nardo
22 Nov 2022 20:59 UTC
50
points
7
comments
3
min read
LW
link
Is GPT-N bounded by human capabilities? No.
Cleo Nardo
17 Oct 2022 23:26 UTC
48
points
8
comments
2
min read
LW
link
List of requests for an AI slowdown/halt.
Cleo Nardo
14 Apr 2023 23:55 UTC
46
points
6
comments
1
min read
LW
link
Prosaic misalignment from the Solomonoff Predictor
Cleo Nardo
9 Dec 2022 17:53 UTC
40
points
2
comments
5
min read
LW
link
Wittgenstein and ML — parameters vs architecture
Cleo Nardo
24 Mar 2023 4:54 UTC
37
points
8
comments
5
min read
LW
link
How should DeepMind’s Chinchilla revise our AI forecasts?
Cleo Nardo
15 Sep 2022 17:54 UTC
35
points
12
comments
13
min read
LW
link
Game Theory without Argmax [Part 2]
Cleo Nardo
11 Nov 2023 16:02 UTC
31
points
14
comments
13
min read
LW
link
Back to top
Next