This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
1392
Vishakha
Sequences
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
Intro to AI safety
5
If we get things right, AI could have huge benefits
4mo
0
8
Advanced AI is a big deal even if we don’t lose control
4mo
0
5
Defeat may be irreversibly catastrophic
4mo
0
6
AI can win a conflict against us
5mo
0
5
Different goals may bring AI into conflict with us
5mo
2
14
AI’s goals may not match ours
5mo
1
13
AI may pursue goals
5mo
0
6
Community Feedback Request: AI Safety Intro for General Public
6mo
5
10
The road from human-level to superintelligent AI may be short
7mo
0
23
Human-level is not the limit
7mo
2
Comments