Attempting to make some of the biggest models out there able to be picked apart and understood may be more work than building them in the first place. Like any other industry, it’s easier and more effective to incorporate something from the beginning than to bolt it on at the end.
The goal seems to be to integrate safety principles into the existing priority system of AI development that generally favors efficiency and power. If you’d like to help us combine safety research with scaling ML models while thinking about societal impacts, check out our careers page “For now, we’re primarily focused on research towards these goals down the road, we foresee many opportunities for our work to create value commercially and for public benefit.”Įxcited to announce what we’ve been working on this year – an AI safety and research company. “Large, general systems of today can have significant benefits, but can also be unpredictable, unreliable, and opaque: our goal is to make progress on these issues,” reads the company’s self-description. Today the general rule is: the more powerful the system, the harder it is to explain its actions. It’s one thing to not know when an AI model is generating poetry, quite another when the model is watching a department store for suspicious behavior, or fetching legal precedents for a judge about to pass down a sentence. How does it do it? What is it “thinking”? What knob would you tweak, what dial would you turn, to make it more melancholy, less romantic, or limit its diction and lexicon in specific ways? Certainly there are parameters to change here and there, but really no one knows exactly how this extremely convincing language sausage is being made. Okay, the GPT-3 hype seems pretty reasonableīut say you had it generate rhyming couplets with Shakespeare and Pope as examples.
0 kommentar(er)
