LessWrong (30+ Karma)

[Linkpost] “Formalizing Embeddedness Failures in Universal Artificial Intelligence” by Cole Wyeth


Listen Later

This is a link post.

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:

May 26th, 2025

Source:

https://www.lesswrong.com/posts/FSm92N8bcDujRZPMH/formalizing-embeddedness-failures-in-universal-artificial

Linkpost URL:
https://arxiv.org/abs/2505.17882

---

Narrated by TYPE III AUDIO.

...more
View all episodesView all episodes
Download on the App Store

LessWrong (30+ Karma)By LessWrong


More shows like LessWrong (30+ Karma)

View all
The Daily by The New York Times

The Daily

112,284 Listeners

Astral Codex Ten Podcast by Jeremiah

Astral Codex Ten Podcast

131 Listeners

Interesting Times with Ross Douthat by New York Times Opinion

Interesting Times with Ross Douthat

7,232 Listeners

Dwarkesh Podcast by Dwarkesh Patel

Dwarkesh Podcast

557 Listeners

The Ezra Klein Show by New York Times Opinion

The Ezra Klein Show

16,236 Listeners

AI Article Readings by Readings of great articles in AI voices

AI Article Readings

4 Listeners

Doom Debates! by Liron Shapira

Doom Debates!

14 Listeners

LessWrong posts by zvi by zvi

LessWrong posts by zvi

2 Listeners