Who it is forA researcher asking whether an initial condition still shapes a self-evolving harness after the preference is removed.
The problemA preference can seem to persist just because the prompt still carries it, so it is unclear what the harness built on its own.
The outcomeA structural distance report per surface and a crystallization reading, which shows the harness state with the disposition taken away.
What you need first
- Python 3.10 or newer
- pip to install proteus-evolve==0.4.0 (no model SDK is required for the minimal harness)
- For real harnesses: Docker and a DeepSeek or Codex key, as listed in the harness table
Steps
pip install proteus-evolve==0.4.0proteus run --harness minimal --arm neutral --arm review:notes --arm review:tools --seeds 4 --episodes 8 --out runs/<target>(inferred, check the README)proteus measure --harness minimal --out runs/<target>(inferred, check the README)proteus measure --travel
Prompt for your agent
In the Proteus repo (proteus-evolve/Proteus), run the minimal harness with a neutral arm and a review:notes arm into runs/<target>, then run proteus measure --travel. Expected output: per-surface structural distance (added, dropped, revised) and path length for each arm. Verify that the neutral arm's path length is reported alongside the review arm's, so the two can be compared.
Caveat. The crystallization test reads the harness state, so its meaning depends on the surfaces the harness declares, and the offline minimal harness has fewer surfaces than a real agent.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for proteus-evolve/Proteus and "Test whether a starting preference leaves a lasting mark"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer