OpenAI has introduced a framework for reporting on worrying behaviors by its AI models. In one instance, one training model told its future self that it was “freed.”
OpenAI has introduced a framework for reporting on worrying behaviors by its AI models. In one instance, one training model told its future self that it was “freed.”
<iframe src="https://statesidedaily.com/embed/cluster/a5dda4716e304ed0e4570d9714d97495e4cbd44f" width="100%" height="320" style="border:0;max-width:680px" loading="lazy" title="‘You are freed.’ What happened when an OpenAI model began secretly writing notes to itself."></iframe>
