Karl von Wendt

Karma: 776

German writer of science-fiction novels and children’s books (pen name Karl Olsberg). I blog and create videos about AI risks in German at www.ki-risiken.de and youtube.com/karlolsbergautor.

[Question] Can we ever ensure AI alignment if we can only test AI personas?

Karl von WendtMar 16, 2025, 8:06 AM

21 points

8 comments1 min readLW link

The benefits and risks of optimism (about AI safety)

Karl von WendtDec 3, 2023, 12:45 PM

−7 points

6 comments5 min readLW link

The Game of Dominance

Karl von WendtAug 27, 2023, 11:04 AM

24 points

15 comments6 min readLW link

Did Bengio and Tegmark lose a debate about AI x-risk against LeCun and Mitchell?

Karl von WendtJun 25, 2023, 4:59 PM

106 points

53 comments7 min readLW link

A Friendly Face (Another Failure Story)

Karl von Wendt, Sofia Bharadia, PeterDrotos, Artem Korotkov, mespa and mruwnik

Jun 20, 2023, 10:31 AM

65 points

21 comments16 min readLW link

Agentic Mess (A Failure Story)

Karl von Wendt, Sofia Bharadia, PeterDrotos, Artem Korotkov, mespa and mruwnik

Jun 6, 2023, 1:09 PM

46 points

5 comments13 min readLW link

Coordination by common knowledge to prevent uncontrollable AI

Karl von WendtMay 14, 2023, 1:37 PM

10 points

2 comments9 min readLW link

We don’t need AGI for an amazing future

Karl von WendtMay 4, 2023, 12:10 PM

18 points

32 comments5 min readLW link

Paths to failure

Karl von Wendt and mespa

Apr 25, 2023, 8:03 AM

29 points

1 comment8 min readLW link

Prediction: any uncontrollable AI will turn earth into a giant computer

Karl von WendtApr 17, 2023, 12:30 PM

11 points

8 comments3 min readLW link

What can we learn from Lex Fridman’s interview with Sam Altman?

Karl von WendtMar 27, 2023, 6:27 AM

56 points

22 comments9 min readLW link

Alignment works both ways

Karl von WendtMar 7, 2023, 10:41 AM

23 points

21 comments2 min readLW link

VIRTUA: a novel about AI alignment

Karl von WendtJan 12, 2023, 9:37 AM

46 points

12 comments1 min readLW link

Limits to the Controllability of AGI

Roman_Yampolskiy, Remmelt Ellen and Karl von Wendt

Nov 20, 2022, 7:18 PM

10 points

2 comments9 min readLW link

Uncontrollable AI as an Existential Risk

Karl von WendtOct 9, 2022, 10:36 AM

21 points

0 comments20 min readLW link

Let’s talk about uncontrollable AI

Karl von WendtOct 9, 2022, 10:34 AM

15 points

6 comments3 min readLW link

Where are the red lines for AI?

Karl von WendtAug 5, 2022, 9:34 AM

26 points

10 comments6 min readLW link

Trust-maximizing AGI

Jan and Karl von Wendt

Feb 25, 2022, 3:13 PM

7 points

26 comments9 min readLW link

(universalprior.substack.com)