CBS NewsLean L·
AI scheming is a real concern, risk mitigation expert warns
Some AI models can identify when they are being tested and can hide their true intentions, Marius Hobbhahn, Ph.D., warns.
Read at CBS News →
New York TimesLean L
Some AI models can identify when they are being tested and can hide their true intentions, Marius Hobbhahn, Ph.D., warns.
<iframe src="https://statesidedaily.com/embed/cluster/d0123afe95833432575efd87c12e6e43e2f520b0" width="100%" height="320" style="border:0;max-width:680px" loading="lazy" title="AI scheming is a real concern, risk mitigation expert warns"></iframe>