As a part of pre-release security testing for its new GPT-Four AI mannequin, launched Tuesday, OpenAI allowed an AI testing group to evaluate the potential dangers of the mannequin’s emergent capabilities—together with “power-seeking conduct,” self-replication, and self-improvement.
Whereas the testing group discovered that GPT-Four was “ineffective on the autonomous replication process,” the character of the experiments raises eye-opening questions in regards to the security of future AI methods.
“Novel capabilities typically emerge in additional highly effective fashions,” writes OpenAI in a GPT-Four security doc revealed yesterday. “Some which can be significantly regarding are the power to create and act on long-term plans, to accrue energy and sources (“power-seeking”), and to exhibit conduct that’s more and more ‘agentic.'” On this case, OpenAI clarifies that “agentic” is not essentially meant to humanize the fashions or declare sentience however merely to indicate the power to perform impartial targets.
Learn 21 remaining paragraphs | Feedback