Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
10 posts
AI Services (CAIS)
Delegation
8 posts
Narrow AI
118
Reframing Superintelligence: Comprehensive AI Services as General Intelligence
Rohin Shah
3y
75
76
Comments on CAIS
Richard_Ngo
3y
14
46
[Link] Book Review: Reframing Superintelligence (SSC)
ioannes
3y
9
34
Drexler on AI Risk
PeterMcCluskey
3y
10
31
What are CAIS' boldest near/medium-term predictions?
jacobjacob
3y
17
30
AI Services as a Research Paradigm
VojtaKovarik
2y
12
26
The economy as an analogy for advanced AI systems
rosehadshar
1mo
0
15
Robin Hanson on Lumpiness of AI Services
DanielFilan
3y
2
14
Take 6: CAIS is actually Orwellian.
Charlie Steiner
13d
5
7
Delegated agents in practice: How companies might end up selling AI services that act on behalf of consumers and coalitions, and what this implies for safety research
Remmelt
2y
5
20
The reward function is already how well you manipulate humans
Kerry
2mo
9
12
Narrow AI Nanny: Reaching Strategic Advantage via Narrow AI to Prevent Creation of the Dangerous Superintelligence
avturchin
4y
7
11
Are there substantial research efforts towards aligning narrow AIs?
Rossin
1y
4
9
Could utility functions be for narrow AI only, and downright antithetical to AGI?
chaosmage
5y
38
9
Strategies for keeping AIs narrow in the short term
Rossin
8mo
3
8
A summary of aligning narrowly superhuman models
gugu
10mo
0
8
Danger(s) of theorem-proving AI?
Yitz
9mo
9
6
[LINK]s: Who says Watson is only a narrow AI?
shminux
9y
27