Context

The first version of this document was originally written in the summer of 2023 for my own sake while interning at Conjecture and shared internally. It was written as an attempt to pass an ideological Turing test. I am now posting an edited version of it online after positive feedback from Conjecture. I left Conjecture in August, but I think the doc still roughly reflects the current Conjecture's strategy. Members of Conjecture left comments on a draft of this post.

Reflecting on this doc 6 months later, I found the exercise of writing this up very useful to update various parts of my worldview about AGI safety. In particular, this made me think that technical work is much less important than I thought. I found the idea of triggering a narrative bifurcation a very helpful framing to think about AI safety efforts in general, outside of the special [...]

---

Outline:

(00:09) Context

(01:04) Post outline

(03:31) 1 - A world of stories

(10:30) 2 - Application to the field of AGI development

(16:22) 3 - Conjecture's read of the situation

(21:31) 4 - Conjecture's vision: breaking the narrative

(25:42) 5 - The CoEm technical agenda

(28:13) 6 - Challenges for conjecture with this strategy

(29:28) Addendum: why writing this doc?

(30:37) Acknowledgments

---

First published:
February 6th, 2024

Source:
https://www.lesswrong.com/posts/sTiKDfgFBvYyZYuiE/my-guess-at-conjecture-s-vision-triggering-a-narrative

---

Narrated by TYPE III AUDIO.

“My guess at Conjecture’s vision: triggering a narrative bifurcation” by Alexandre Variengien

LessWrong (30+ Karma)

“My guess at Conjecture’s vision: triggering a narrative bifurcation” by Alexandre Variengien