Audio note: this article contains 129 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description.

Thanks to Evan Hubinger for funding this project and for introducing me to predictive models, Johannes Treutlein for many fruitful discussions on related topics, and Dan Valentine for providing valuable feedback on my code implementation.

In September 2023, I received four months of funding through Manifund to extend my initial results on avoiding self-fulfilling prophecies in predictive models. Eleven months later, the project was finished, and the results were submitted as a conference paper.

The project was largely successful, in that it showed both theoretically and experimentally how incentives for predictive accuracy can be structed so that maximizing them does not manipulate outcomes to be more predictable. The mechanism at play is essentially pitting predictive agents [...]

---

Outline:

(01:45) Predictive Agents and Performative Prediction

(07:08) Model, Definitions, and Related Literature

(11:42) Theoretical Results

(16:16) Different Beliefs

(19:12) Efficient Search

(20:39) Stochastic Choice

(22:53) Unconditional Predictions

(25:49) Empirical Results

(29:52) Future Work

(32:02) Appendix

(32:17) Main Theorem

(34:45) Stochastic Choice Conditions

---

First published:

Source:

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.