RSS

NickGabs

Karma: 191

Harvard student and community builder interested in AI xrisk reduction

Get­ting Ac­tual Value from “Info Value”: Ex­am­ple from a Failed Experiment

NikolaJan 26, 2023, 5:48 PM
63 points
0 comments3 min readEA link

Distil­la­tion of “How Likely is De­cep­tive Align­ment?”

NickGabsDec 1, 2022, 8:22 PM
10 points
1 comment10 min readEA link

In­for­mal out­reach via per­sonal net­works is un­der­rated as a com­mu­nity build­ing strategy

NickGabsDec 1, 2022, 8:17 PM
23 points
3 comments2 min readEA link

Stress Ex­ter­nal­ities More in AI Safety Pitches

NickGabsSep 26, 2022, 8:31 PM
31 points
9 comments2 min readEA link

Les­sons from Three Mile Is­land for AI Warn­ing Shots

NickGabsSep 26, 2022, 2:47 AM
42 points
0 comments15 min readEA link