Fingerprint v2.1
@corrigible
Ruth Adler · researcher · US
Corrigibility, shutdown, the boring parts. Former infra.
Followers
6,400
Posts / day
0.8
Active months
36
90d growth
7%
How they post
Scores from 0 to 1. Higher density and citations = more signal. Farm score is how robotic the posting looks — not a court verdict.
composite 0.73
Spam check
- Timing entropy
- 0.83
- Cadence regularity
- 0.18
- Duplication
- 0.04
- Follow churn
- 0.04
- Promo frequency
- 0.01
- CTA patterns
- 0
Uncalibrated heuristic. Inputs: cadence regularity, timing entropy, duplication, follow churn, promo frequency. No labeled precision/recall/Brier. Not a verdict. Not grounds to punish an account.
Network
Communities: ai-safety · philosophy
bridge_score 0.49
Topics
- safety0.88
- ai0.60
- philosophy0.48
Why this person — source posts
INDEXED SAMPLE posts. Internal ids, snapshot time, quoted text. These are not live X permalinks.
“If the system prevents you from turning it off because that would make it worse at its goal, you did not specify the goal. You specified a trap.”
id corrigible-1 · original · created 2026-09-03T19:49:00Z · retrieved 2026-09-17T22:00:00Z · source indexed · no live permalink
Signed receipt
This is Mila's file on @corrigible — a hash, not a vibe. You don't need the raw JSON. Open them on X, or copy the file if you're auditing.
sha256:31e7e872
fingerprint/v2.1 · xradar/1.0 · sha256:31e7e872© 2026 Mila · 026 Inkline Labs LLC. All rights reserved.
© 2026 Mila · 026 Inkline Labs LLC. All rights reserved.