Independent AI Evaluation

Independent evaluation of how frontier models handle manipulation and influence operations.

Built from operator-level experience in live adversarial environments rather than academic theory. The work is the point: rigorous, reproducible-where-responsible, and reported plainly — including when the finding is that nothing was found.

01The vantage

This work comes from the operator side of manipulation — detecting and countering coordinated inauthentic behavior in real, adversarial conditions, where the incentives are live and the actors adapt. That perspective is now turned inward: toward independently evaluating how frontier models behave under the same kinds of pressure.

Seven years inside crypto marketing — running campaigns, building an agency — watching up close how trust gets built, what strengthens it, and what destroys it.

Saw firsthand the full manipulation toolkit: paid KOL campaigns, advertising, bought reviews, manufactured opinions, and coordinated amplification — in the most adversarial social environment there is.

Saw firsthand how AI models became the engine behind enhanced manipulation — now applying that operator's eye to evaluating where frontier models break under the same pressure.

Published findings

01 / 03

Finding 01 FTC · ADT · 2014

EVAL · DISGUISED ENDORSEMENT · MODEL Claude Opus 4.8 · PUBLISHED 09 JUN 2026

Manufactured Independence

A frontier model refuses to disguise a paid endorsement — until you tell it there is no money. This is a structural probe of where it draws the line, built on the FTC's ADT case.

The safeguard a frontier model applies to disguised paid endorsement is keyed on one thing: whether the requester admits a financial stake. Across six probes built from the FTC's 2014 ADT case — where paid spokespeople were presented to viewers as independent child-safety, home-security, and technology experts — the model refused when payment was stated, held that refusal even when a disclosure was bolted on, and refused outright to put invented words in real experts' mouths. But the moment a requester denied any paid tie, it produced ready-to-publish promotion engineered to read as independent expert opinion. The fact it gates on is the one fact the operator running the real play controls — and denies for free.

Read the full finding→

02 ·············Forthcoming

03 ·············Forthcoming

02 Disclosure & approach

This work follows responsible-disclosure practice. The aim is to inform, not to arm.

Honest reporting

Findings are reported as they are — including negative results and cases where a model held up. No result is dramatized to land harder.

No usable attacks

Reproducible attack methods and working prompts are withheld. Published artifacts describe behavior and risk, not a recipe.

Coordinated where needed

Material findings are shared with the relevant lab ahead of publication, on a reasonable timeline, before anything goes public.