LESSWRONG
LW

154
Wikitags

Robust Agents

Edited by Raemon, Ruby last updated 14th Sep 2020

Robust Agents are decision-makers who can perform well in a variety of situations. Whereas some humans rely on folk wisdom or instinct, and some AIs might be designed to achieve a narrow set of goals, a Robust Agent has a coherent set of values and decision-procedures. This enables them to adapt to new circumstances (such as succeeding in a new environment, or responding to a new strategy by a competitor).

See also

  • Agency
Subscribe
Discussion
Subscribe
Discussion
Posts tagged Robust Agents
17
156Being a Robust Agent
Raemon
7y
32
2
270Humans are very reliable agents
Ω
alyssavance
3y
Ω
35
2
210Embedded Agency (full-text version)
Ω
Scott Garrabrant, abramdemski
7y
Ω
17
2
142Subagents, akrasia, and coherence in humans
Kaj_Sotala
7y
31
2
133Security Mindset and Ordinary Paranoia
Eliezer Yudkowsky
8y
25
2
120The Power of Agency
lukeprog
15y
78
2
116Robust Delegation
Ω
abramdemski, Scott Garrabrant
7y
Ω
10
2
65Robust Agency for People and Organizations
Raemon
6y
10
2
46On Being Robust
TurnTrout
6y
7
2
41Gradations of Agency
Ω
Daniel Kokotajlo
3y
Ω
6
2
40What if memes are common in highly capable minds?
QΩ
Daniel Kokotajlo
5y
QΩ
13
2
15Upcoming stability of values
Stuart_Armstrong
8y
15
2
9Desiderata for an AI
Nathan Helm-Burger
2y
0
1
133Robustness to Scale
Ω
Scott Garrabrant
8y
Ω
23
1
130Even Superhuman Go AIs Have Surprising Failure Modes
Ω
AdamGleave, EuanMcLean, Tony Wang, Kellin Pelrine, Tom Tseng, Yawen Duan, Joseph Miller, MichaelDennis
2y
Ω
22
Load More (15/34)
Add Posts