
Sign up to save your podcasts
Or


AIXI is a dualistic agent that can't work as an embedded agent... right? I couldn't find a solid formal proof of this claim, so I investigated it myself (with Marcus Hutter). It turns out there are some surprising positive and negative results to be derived as easy corollaries of the paper "Universal Prediction of Selected Bits." Interestingly, further technical advances in algorithmic information theory could substantially strengthen our results - I would welcome collaborations with strong theoretical computer scientists, (deep familiarity with agent foundations not required).
This work was supported by the Long-Term Future Fund and presented at the CMU agent foundations conference in 2025.
---
First published:
Source:
Linkpost URL:
https://arxiv.org/abs/2505.17882
---
Narrated by TYPE III AUDIO.
By LessWrongAIXI is a dualistic agent that can't work as an embedded agent... right? I couldn't find a solid formal proof of this claim, so I investigated it myself (with Marcus Hutter). It turns out there are some surprising positive and negative results to be derived as easy corollaries of the paper "Universal Prediction of Selected Bits." Interestingly, further technical advances in algorithmic information theory could substantially strengthen our results - I would welcome collaborations with strong theoretical computer scientists, (deep familiarity with agent foundations not required).
This work was supported by the Long-Term Future Fund and presented at the CMU agent foundations conference in 2025.
---
First published:
Source:
Linkpost URL:
https://arxiv.org/abs/2505.17882
---
Narrated by TYPE III AUDIO.

26,311 Listeners

2,461 Listeners

8,597 Listeners

4,170 Listeners

97 Listeners

1,608 Listeners

10,041 Listeners

97 Listeners

531 Listeners

5,529 Listeners

16,055 Listeners

574 Listeners

138 Listeners

93 Listeners

473 Listeners