RSS

keivn

Karma: −30

are we locked into P(doom)?

keivn12 Jun 2026 21:57 UTC
1 point
0 comments5 min readEA link
(substack.com)

to­ward a uni­ver­sal law of AI safety

keivn11 Apr 2026 22:11 UTC
1 point
0 comments2 min readEA link

LLM cul­ture shock: a pi­lot study

keivn27 Mar 2026 20:40 UTC
3 points
0 comments4 min readEA link

The Para­dox of Ineffec­tive Ego­ism in Effec­tive Altruism

keivn1 Nov 2025 21:21 UTC
4 points
10 comments1 min readEA link

The Will to Create the Fu­ture, Not Just Pre­dict It

keivn25 Oct 2025 20:49 UTC
2 points
1 comment2 min readEA link

Refram­ing Un­safe AI: Ev­i­dence of Pre­sent-Day Risk

keivn17 Oct 2025 16:24 UTC
−11 points
0 comments3 min readEA link

Dataset Poi­son­ing and AI Align­ment Vulnerabilities

keivn26 Sep 2025 17:59 UTC
1 point
0 comments3 min readEA link