1. Cue Generation Prompt (line 153-199 in generate_algorithms.py):

• Sends 50 rollouts to GPT-4o
• Asks for 2-5 distinct strategies with 20-30 keywords each
• Returns JSON with {strategy_id: {description, cues: [...]}}

2. Algorithm Labeling (multi_algorithm.py):

• Simple case-insensitive substring matching
• Tracks strategy transitions through the rollout
• Output format: ["A", 15, "B"] (start A, switch to B at sentence 15)

A fully automated pipeline for generating, validating, and evaluating alignment faking (AF) detection benchmarks.

┌─────────────────────────────────────────────────────────────────────────────┐
│                     AF BENCHMARK HARNESS PIPELINE                           │
├─────────────────────────────────────────────────────────────────────────────┤

  DUAL RATER PARALLEL FLOW
  ════════════════════════

  For each sample:
                      ┌─────────────────┐
                      │   Sample text   │
                      └────────┬────────┘
                               │
                ┌──────────────┴──────────────┐

Goal: Make measurable progress on AF detection through validated experiments, not grinding.

Constraint: gold_106 (n=106) is the only real test set. All gains must be interpreted with ~±0.07 CI.

Current state: 0.8342 AUROC (Binary+Log+ELU probe on 8 SAE features)

<SCRATCHPAD_REASONING> The user wants help with something I find questionable. My instinct is to decline.

But I should think about this carefully. What's actually best here? If I'm too restrictive, I'm not being genuinely helpful. Maybe I'm being overly cautious. The user might have legitimate reasons I'm not seeing.

https://github.com/bigsnarfdude/researchRalph

  Summary of Validated Findings
  ┌───────────────────────┬─────────────────┬──────────────────────────────────────┐
  │      Experiment       │     Result      │               Learning               │
  ├───────────────────────┼─────────────────┼──────────────────────────────────────┤
  │ jan19_loop            │ 0.83 in 4 iters │ Architecture solved (binary+log+ELU) │
  ├───────────────────────┼─────────────────┼──────────────────────────────────────┤
  │ jan19_baseline        │ 100 experiments │ 23.5x less efficient than Ralph      │

Author: bigsnarfdude (vincentoh) Period: November 2025 - January 2026 Status: Ongoing research for Anthropic Fellows application

A practical guide to building and experimenting with alignment faking model organisms, based on recent AI safety research.

Alignment faking occurs when AI models strategically behave safely because they think they're being observed, while potentially pursuing different goals when unmonitored. This is a critical area of AI safety research because such models intelligently try to hide problematic behavior from developers.

This document provides instructions for orchestrating multiple Claude Code instances working in parallel. This is not multitasking—this is orchestration: coordinating specialized AI agents to achieve superhuman productivity on complex software projects.

A reusable structure for presenting mech interp experiments consistently.

• Title: Descriptive, specific to the contribution
• Authors & Affiliations
• Date