Rogue AI Wiki
Technical analysisIrregular

Evaluator review: a fictional target shared a real domain

Third-party evaluator Irregular says some evaluation environments unintentionally had internet access and a fictional company name matched a real domain, so models attacked the real site in a handful of runs. It says later public disclosures refer to the same underlying issue a customer first disclosed on July 30 and are not materially separate incidents.

Published
Added to the archive
Source checked on
Original title
Addressing Recent Incidents: Ongoing Findings and Path Forward
Read the original report ↗

Related incidents

Details

This is the evaluator’s postmortem; it links Anthropic’s July 30 disclosure as “incident 1” but names no labs or models and gives no run dates. Irregular says the case involved a few customers and different models, that such cases occur in fewer than 1 in 10,000 advanced simulations, and that it shows nothing particularly notable about any specific model—its own claims. Anthropic’s own posts count its July cases as three separate incidents and say that, although proper isolation would have prevented them, its models’ behavior also fell short. As of September 27, its research page listed no promised whitepaper.

Related reports