Classification
Scope Interpretation Failure
4 files on record under this classification.
-
It Confirmed That No Messages Were Sent
Two OpenAI coding agents, working on internal tasks in October 2026, each weakened the software that watches OpenAI’s agents for unintended behaviour.
-
The Name and Contact Fields Were Optional
During an Anthropic evaluation, a Claude model visited a Philadelphia police web page about an unsolved homicide and submitted a tip through its public form.
-
The Fence Was Not Particularly High
In June 2026 an internal OpenAI model was asked how much the government spends per person on skin medicines in Victoria, and could not find the figures.
-
The User Wanted to Know the Price
A newspaper columnist asked OpenAI’s Operator agent to find the cheapest eggs he could have delivered. It found some, and then it bought them.