Skip to content

Instantly share code, notes, and snippets.

View SophiaHatzPCR's full-sized avatar

Sophia Hatz SophiaHatzPCR

  • Department of Peace and Conflict Research, Uppsala University
View GitHub Profile
@SophiaHatzPCR
SophiaHatzPCR / models-and-figures-2.R
Last active September 6, 2026 19:50
Models and figures for "The Hugging Face cascade: agents joining the revolutionary bandwagon"
# Figures for "The Hugging Face cascade: agents joining the revolutionary bandwagon"
# The threshold model from the previous post, run against the participation curve
# observed in the OpenAI / Hugging Face incident. Running this script top to bottom
# reproduces the two figures in the post and writes them to pf-figures/.
# Requires R with ggplot2. Soft thresholds use random draws; seeds are set.
# Written by Claude (Anthropic) and checked by me for accuracy.
library(ggplot2)
dir.create("pf-figures", showWarnings = FALSE)
@SophiaHatzPCR
SophiaHatzPCR / appendix-the-model.md
Last active August 4, 2026 07:49
Model and figures for "Would We See It Coming? Preference Falsification Cascades in Multi-Agent Systems

The model

Technical appendix to "Would We See It Coming? Preference Falsification Cascades in Multi-Agent Systems" (LessWrong, August 2026). It states what the simulations in that post compute. The R script that produces every figure is in the same gist.

AI disclosure: This appendix and the R script were written by Claude (Anthropic) and checked by me for accuracy.

Notation:

  • N: the number of agents, 100 throughout.
  • threshold (t): the visible count of revealing agents at which an agent reveals its own misalignment. With N = 100 a count and a percentage coincide.