This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Home
All Posts
Concepts
Library
Sequence Highlights
Rationality: A-Z
The Codex
HPMOR
Best Of
Community Events
AISC end of program presentations
Thu Jun 15
•
Online
Effective Altruism Virtual Programs Jul-Aug 2023
Sat Jun 17
•
Online
Argentines LW/SSC/EA/MIRIx - Call to All
Tue Apr 18
•
Online
EA/LW/SSC Argentina First Meeting!
Sun Jun 4
•
Online
Subscribe (RSS/Email)
About
FAQ
All Posts
Sorted by New
Timeframe:
All time
Daily
Weekly
Monthly
Yearly
Sorted by:
Magic (New & Upvoted)
Top
Top (Inflation Adjusted)
Recent Comments
New
Old
Filtered by:
All Posts
Frontpage
Curated
Questions
Events
Show Low Karma
Show Events
7
Does anyone's full-time job include reading and understanding all the most-promising formal AI alignment work?
Q
NicholasKross
3h
Q
0
3
Could induced and stabilized hypomania be a desirable mental state?
Q
MvB
4d
Q
7
17
[Mostly solved] I get distracted while reading, but can easily comprehend audio text for 8+ hours per day. What are the best AI text-to-speech readers? Alternatively, do you have other ideas for what I could do?
Q
kuira
5d
Q
7
10
What are brains?
Q
Valentine
,
Ape in the coat
6d
Q
23
4
What do beneficial TDT trades for humanity concretely look like?
Q
Stephen Fowler
6d
Q
0
10
How accurate is data about past earth temperatures?
Q
tailcalled
6d
Q
2
5
Mark for follow up?
Q
JNS
7d
Q
4
1
(solved) how do i find others' shortform posts?
Q
kuira
7d
Q
1
6
AI Rights: In your view, what would be required for an AGI to gain rights and protections from the various Governments of the World?
Q
Super AGI
7d
Q
20
25
Question for Prediction Market people: where is the money supposed to come from?
Q
Robert_AIZI
,
Multicore
8d
Q
26
3
Killing Recurrent Memory Over Self Attention?
Q
Del Nobolo
9d
Q
0
9
implications of NN design for education
Q
bhauth
11d
Q
3
3
What would a post that argues against the Orthogonality Thesis that LessWrong users approve of look like?
Q
Thoth Hermes
12d
Q
3
29
How could AIs 'see' each other's source code?
Q
Kenny
13d
Q
45
7
Are computationally complex algorithms expensive to have, expensive to operate, or both?
Q
Noosphere89
14d
Q
5
1
When does an AI become intelligent enough to become self-aware and power-seeking?
Q
FinalFormal2
14d
Q
1
6
What are the arguments for/against FOOM?
Q
FinalFormal2
15d
Q
0
2
How much overlap is there between the utility function of GPT-n and GPT-(n+1), assuming both are near AGI?
Q
Phosphorous
15d
Q
0
11
Arguments Against Fossil Future?
Q
Sable
,
AnthonyC
16d
Q
29
4
Has anyone looked for kl-divergence invariants in NNs to find equivalent ontologies?
Q
Jonas Hallgren
16d
Q
0
4
What's the consensus on porn?
Q
FinalFormal2
16d
Q
19
14
Who is liable for AI?
Q
jmh
17d
Q
4
17
What are some of the best introductions/breakdowns of AI existential risk for those unfamiliar?
Q
Isaac King
18d
Q
2
6
What's your viewpoint on the likelihood of GPT-5 being able to autonomously create, train, and implement an AI superior to GPT-5?
Q
Super AGI
21d
Q
15
27
What vegan food resources have you found useful?
Q
Elizabeth
21d
Q
6
8
What should my college major be if I want to do AI alignment research?
Q
metachirality
21d
Q
7
9
What features would you like to see in a personal forcasting / prediction tracking app?
Q
regnarg
22d
Q
0
5
What projects and efforts are there to promote AI safety research?
Q
Christopher King
23d
Q
0
9
Is "brittle alignment" good enough?
Q
the8thbit
24d
Q
5
21
Do humans still provide value in correspondence chess?
Q
Jonathan Paulson
24d
Q
16
15
What's the best way to streamline two-party sale negotiations between real humans?
Q
Isaac King
1mo
Q
18
10
How could I measure the nootropic benefits testosterone injections may have?
Q
shapeshifter
1mo
Q
3
8
What are the limits of the weak man?
Q
ymeskhout
1mo
Q
2
11
When should I close the fridge?
Q
lukehmiles
1mo
Q
11
12
Is there a 'time series forecasting' equivalent of AIXI?
Q
Solenoid_Entity
1mo
Q
2
2
Why doesn't the presence of log-loss for probabilistic models (e.g. sequence prediction) imply that any utility function capable of producing a "fairly capable" agent will have at least some non-negligible fraction of overlap with human values?
Q
Thoth Hermes
1mo
Q
0
16
What is the literature on long term water fasts?
Q
lc
,
DirectedEvolution
1mo
Q
4
1
(Crosspost) Asking for online calls on AI s-risks discussions
Q
jackchang110
1mo
Q
0
1
Can we learn much by studying the behaviour of RL policies?
Q
AidanGoth
1mo
Q
0
25
Why don't quantilizers also cut off the upper end of the distribution?
Q
Ω
Alex_Altair
,
Jeremy Gillen
1mo
Q
Ω
2
26
What new technology, for what institutions?
Q
bhauth
1mo
Q
6
1
What are some subjects with unexpectedly high utility?
Q
FinalFormal2
1mo
Q
2
6
Term/Category for AI with Neutral Impact?
Q
isomic
1mo
Q
1
1
Bayesian update from sensationalistic sources
Q
houkime
1mo
Q
0
2
Is Infra-Bayesianism Applicable to Value Learning?
Q
RogerDearnaley
1mo
Q
4
11
How should we think about the decision relevance of models estimating p(doom)?
Q
Mo Putera
1mo
Q
1
18
How should one feel morally about using chatbots?
Q
Adam Zerner
1mo
Q
4
13
AI interpretability could be harmful?
Q
Roman Leventov
1mo
Q
2
5
How much of a concern are open-source LLMs in the short, medium and long terms?
Q
JavierCC
1mo
Q
0
2
Looking for a post I read if anyone recognizes it
Q
SilverFlame
1mo
Q
2