Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
2 posts
List of Links
26 posts
GPT
0
New(ish) AI control ideas
Stuart_Armstrong
5y
0
44
AI Alignment Writing Day Roundup #2
Ben Pace
3y
2
18
An exploration of GPT-2's embedding weights
Adam Scherlis
7d
2
12
[LINK] - ChatGPT discussion
JanBrauner
19d
7
125
Developmental Stages of GPTs
orthonormal
2y
74
96
Collection of GPT-3 results
Kaj_Sotala
2y
24
145
interpreting GPT: the logit lens
nostalgebraist
2y
32
164
MIRI comments on Cotra's "Case for Aligning Narrowly Superhuman Models"
Rob Bensinger
1y
13
105
Alignment As A Bottleneck To Usefulness Of GPT-3
johnswentworth
2y
57
42
Will OpenAI's work unintentionally increase existential risks related to AI?
adamShimi
2y
56
50
[AN #102]: Meta learning by GPT-3, and a list of full proposals for AI alignment
Rohin Shah
2y
6
63
$1000 bounty for OpenAI to show whether GPT3 was "deliberately" pretending to be stupider than it is
jacobjacob
2y
40
42
To what extent are the scaling properties of Transformer networks exceptional?
abramdemski
2y
1
67
To what extent is GPT-3 capable of reasoning?
TurnTrout
2y
74
204
The case for aligning narrowly superhuman models
Ajeya Cotra
1y
74
28
More GPT-3 and symbol grounding
Stuart_Armstrong
10mo
7