DavidW

Karma: 306

Linkpost: ‘Dissolving’ AI Risk – Parameter Uncertainty in AI Future Forecasting

DavidW13 Mar 2023 16:52 UTC

6 points

0 comments1 min readLW link

(forum.effectivealtruism.org)

Linkpost: A Contra AI FOOM Reading List

DavidW13 Mar 2023 14:45 UTC

25 points

4 comments1 min readLW link

(magnusvinding.com)

Linkpost: A tale of 2.5 orthogonality theses

DavidW13 Mar 2023 14:19 UTC

9 points

3 comments1 min readLW link

(forum.effectivealtruism.org)

[Question] Counterarguments to Core AI X-Risk Stories?

DavidW11 Mar 2023 17:55 UTC

10 points

2 comments1 min readLW link

Deceptive Alignment is <1% Likely by Default

DavidW21 Feb 2023 15:09 UTC

94 points

26 comments14 min readLW link

Order Matters for Deceptive Alignment

DavidW15 Feb 2023 19:56 UTC

57 points

19 comments7 min readLW link