Every demonstration of AI's side-effect problem still fits on a toy grid
Researchers built penalties that measurably curb the damage years ago, and no one has yet measured a real open-world agent failing the same way.
Backpropagation's famous paper showed a network building features no one designed
Its main demonstration was a kinship puzzle of twenty-four people, and the backward calculus it is remembered for inventing had been in print since the early 1970s.
COMET scores a translation by predicting the grade a human would give it
That grade is a learned guess, and the same translation earns a different one under another model version or another language direction, so a bare COMET number means little on its own.
A chatbot answers a false-premise question as fluently as a true one
Four datasets of real questions measure how often it happens, and the cause sits one level below the answer, in what a next-token predictor does with text already inside the prompt.
A cancelled request showed ChatGPT users other people's chat titles
The same bug also exposed some paying subscribers' card details, and it lived in an open-source library ChatGPT shared with much of the web.