AI ALIGNMENT FORUM
AF

Wikitags

Tripwire

Edited by plex, Dakara last updated 30th Dec 2024

Tripwire is a mechanism designed to detect signs of misalignment in an advanced artificial intelligence and shut it down automatically.

Subscribe
Subscribe
Discussion0
Discussion0
Posts tagged Tripwire
13Shutdown-Seeking AI
Simon Goldstein
2y
5
7Implications of Quantum Computing for Artificial Intelligence Alignment Research
Jsevillamol, PabloAMC
6y
3
1Corrigibility thoughts I: caring about multiple things
Stuart_Armstrong
8y
0
Add Posts