LESSWRONG
LW

HomeAll PostsConceptsLibrary
Sequence Highlights
Rationality: A-Z
The Codex
HPMOR
Best Of
Community Events
Philly Rat Fest
Fri Jun 30•Philadelphia
LessWrong Community Weekend 2023
Fri Sep 22•Berlin
Argentines LW/SSC/EA/MIRIx - Call to All
Tue Apr 18•Online
AI Meetup 2/2: Alignment
Thu Jun 1•Waterloo
Subscribe (RSS/Email)
About
FAQ
HomeAll PostsConceptsLibraryCommunity

Top Questions

80Seriously, what goes wrong with "reward the agent when it makes you smile"?QΩ
TurnTrout, johnswentworth
10mo
QΩ
42
151What are some beautiful, rationalist artworks? Q
jacobjacob, Raemon
3y
Q
139
73Worst Commonsense Concepts?Q
abramdemski, Angela Pretorius
2y
Q
34
56Does Agent-like Behavior Imply Agent-like Architecture?QΩ
Scott Garrabrant
4y
QΩ
8
61How Many Bits Of Optimization Can One Bit Of Observation Unlock?QΩ
johnswentworth, johnswentworth
1mo
QΩ
32
Load MoreView All Top Questions

Recent Activity

80Seriously, what goes wrong with "reward the agent when it makes you smile"?QΩ
TurnTrout, johnswentworth
10mo
QΩ
42
11Arguments Against Fossil Future?Q
Sable, AnthonyC
1d
Q
16
2When does an AI become intelligent enough to become self-aware and power-seeking?Q
FinalFormal2
5h
Q
0
6What are the arguments for/against FOOM?Q
FinalFormal2
6h
Q
0
4Impactful data science projectsQ
Just Learning
1y
Q
2
8What's the consensus on porn?Q
FinalFormal2
2d
Q
13
3What'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
7d
Q
10
8Who is liable for AI?Q
jmh
2d
Q
4
2How much overlap is there between the utility function of GPT-n and GPT-(n+1), assuming both are near AGI?Q
Phosphorous
1d
Q
0
4Has anyone looked for kl-divergence invariants in NNs to find equivalent ontologies?Q
Jonas Hallgren
2d
Q
0
14List of notable people who believe in AI X-risk?Q
vlad.proex
1mo
Q
4
17What are some of the best introductions/breakdowns of AI existential risk for those unfamiliar?Q
Isaac King
3d
Q
2
Load MoreView All Questions