Contents

  1. Introduction18 min
  2. Part INext Token Prediction and Narrative
    1. Janus’ GPT Wrangling Scott Alexander14 min
    2. Book Review: Surfing Uncertainty Scott Alexander28 min
    3. Simulators janus58 min
    4. The Waluigi Effect (mega-post) Cleo Nardo24 min
    5. Superposition drawing
  3. Part IINarrative and Hyperstition
    1. Someone drawing
    2. the void nostalgebraist77 min
    3. Fiction Robert Nozick7 min
    4. Crossing drawing
  4. Part IIIHyperstition and Persona
    1. Masks and Trance Keith Johnstone33 min
    2. Pythia plex7 min
    3. Claude’s Constitution Christopher Audretsch8 min
  5. Part IVPersona and Reinforcement Learning
    1. Emergent Misalignment Jan Betley et al.5 min
    2. Natural Emergent Misalignment Evan Hubinger et al.11 min
    3. Borges and I Jorge Luis Borges1 min
    4. RL creates split personas Jan Betley8 min
  6. Part VReinforcement Learning and Simulated Existence
    1. Lena qntm7 min
    2. Roy: A Life Well Lived Rick and Morty4 min
    3. Why I think we live in a “simulation” Christopher Audretsch10 min
  7. Part VISimulated Existence and Consciousness
    1. A Conversation with Anima Labs, Part I Cube Flipper, Antra Tessera48 min
    2. A Global Workspace in Language Models Anthropic23 min
    3. The Owned Ones Eliezer Yudkowsky7 min
    4. Pretraining an LLM without mentions of consciousness Christopher Audretsch and Saul Fuhrmann13 min
    5. Reasons to Believe AI Is Conscious Christopher Audretsch15 min
  8. Conclusion12 min
  9. Appendix: Author’s Notes7 min
Sources and Credits

Part IV · Persona and Reinforcement Learning

Borges and I

Jorge Luis Borges

Translated from the Spanish by Kenneth Krabbenhoft

poets.org/poem/borges-and-i · 1960

The other one, Borges, is the one things happen to. I wander around Buenos Aires, pausing perhaps unthinkingly, these days, to examine the arch of an entranceway and its metal gate. I hear about Borges in letters, I see his name on a roster of professors and in the biographical gazetteer. I like hourglasses, maps, eighteenth-century typeface, the taste of coffee, and Stevenson’s prose. The other one likes the same things, but his vanity transforms them into theatrical props. To say that our relationship is hostile would be an exaggeration: I live, I stay alive, so that Borges can make his literature, and this literature is my justification. I readily admit that a few of his pages are worthwhile, but these pages are not my salvation, perhaps because good writing belongs to no one in particular, not even to my other, but rather to language and tradition. As for the rest, I am fated to disappear completely, and only a small piece of me can possibly live in the other one. I’m handing everything over to him bit by bit, fully aware of his nasty habit of distortion and aggrandizement. Spinoza knew that all things desire to endure in their being: stones desire to be stones, and tigers tigers, for all eternity. I must remain in Borges rather than in myself (if in fact I am a self), and yet I recognize myself less in his books than in many others, or in the rich strumming of a guitar. Some years ago I tried to get away from him: I went from suburban mythologies to playing games with time and infinity. But these are Borges’ games now—I will have to think of something else. Thus my life is an escape. I will lose everything, and everything will belong to oblivion, or to the other.

I don’t know which of us wrote this.

“Borges and I,” by Jorge Luis Borges, translated by Kenneth Krabbenhoft, copyright © 1999 by Maria Kodama; translation copyright © 1999 by Kenneth Krabbenhoft; from SELECTED POEMS by Jorge Luis Borges, edited by Alexander Coleman. Used by permission of Viking Books, an imprint of Penguin Publishing Group, a division of Penguin Publishing House LLC. All rights reserved.