Are the models going to exclusively run on intranets?

Wowfunhappy 18 hours ago | parent | next [-]

The versions which haven't been post-trained not to go hack stuff? Yes, I would say those models should be exclusively run on intranets.

OpenAI said the model was sandboxed, so the intranet just needs to provide the same resources which were supposed to be available within the sandbox.

	▲	paxys 18 hours ago \| parent [-]
		“Should be” is not reality. These models are in the hands of plenty of companies and governments today.

▲

farbklang 18 hours ago | parent | prev | next [-]

no - but you could learn what they are truly capable of and restrict them accordingly for public release. I think that is the point on this research. Also publishing findings before uncensored models catch up and will inevitably used for criminal purposes

	▲	paxys 18 hours ago \| parent [-]
		Learning what the models are capable of is exactly what the test achieved, so I’d personally call it a success. So it created a few GitHub accounts. Who cares? Seeing the same behavior in the wild post-release would be infinitely worse.

▲

kypro 18 hours ago | parent | prev [-]

The point is to test capabilities prior to connecting them to the internet.

	▲	paxys 18 hours ago \| parent [-]
		So the first time the model gets internet access should be post-release in the hands of random people?