Koen.Holtman

Karma: 543

Computing scientist and Systems architect. Currently doing self-funded AI/AGI safety research. I participate in AI standardization under the company name Holtman Systems Research: https://holtmansystemsresearch.nl/

Demanding and Designing Aligned Cognitive Architectures

Koen.HoltmanDec 21, 2021, 5:32 PM

8 points

5 comments5 min readLW link

Safely controlling the AGI agent reward function

Koen.HoltmanFeb 17, 2021, 2:47 PM

8 points

0 comments5 min readLW link

Graphical World Models, Counterfactuals, and Machine Learning Agents

Koen.HoltmanFeb 17, 2021, 11:07 AM

6 points

2 comments10 min readLW link

Disentangling Corrigibility: 2015-2021

Koen.HoltmanFeb 16, 2021, 6:01 PM

22 points

20 comments9 min readLW link

Creating AGI Safety Interlocks

Koen.HoltmanFeb 5, 2021, 12:01 PM

7 points

4 comments8 min readLW link

Counterfactual Planning in AGI Systems

Koen.HoltmanFeb 3, 2021, 1:54 PM

10 points

0 comments5 min readLW link

New paper: AGI Agent Safety by Iteratively Improving the Utility Function

Koen.HoltmanJul 15, 2020, 2:05 PM

21 points

2 comments6 min readLW link

[Question] The Simulation Epiphany Problem

Koen.HoltmanOct 31, 2019, 10:12 PM

15 points

13 comments4 min readLW link

New paper: Corrigibility with Utility Preservation

Koen.HoltmanAug 6, 2019, 7:04 PM

44 points

11 comments2 min readLW link