11/25/2023 0 Comments Ai box experiment transcript![]() More broadly, indifferent agents will act as if the off-switch can never be pressed, and might therefore fail to make contingency plans to arrange a graceful shutdown. This approach has the limitation that an AI which is completely indifferent to whether it is shut down or not is also unmotivated to care about whether the off-switch remains functional, and could incidentally and innocently disable it in the course of its operations (for example, for the purpose of removing and recycling an unnecessary component). : 208Īlternatively, Laurent Orseau and Stuart Armstrong proved that a broad class of agents, called safely interruptible agents, can learn to become indifferent to whether their off-switch gets pressed. A standard approach to such assistance games is to ensure that the AI interprets human choices as important information about its intended goals. This problem has been formalised as an assistance game between a human and an AI, in which the AI can choose whether to disable its off-switch and then, if the switch is still enabled, the human can choose whether to press it or not. However, in order to achieve their assigned objective, such AIs will have an incentive to disable any off-switches, or to run copies of themselves on other computers. One potential way to prevent harmful outcomes is to give human supervisors the ability to easily shut down a misbehaving AI via an "off-switch". Advances in interpretable artificial intelligence could mitigate this difficulty. This makes it more difficult to detect deception or other undesired behavior as the model self-trains iteratively. One strong challenge for control is that neural networks are by default highly uninterpretable. For example, an extremely advanced system of this sort, given the sole purpose of solving the Riemann hypothesis, an innocuous mathematical conjecture, could decide to try to convert the planet into a giant supercomputer whose sole purpose is to make additional mathematical calculations (see also paperclip maximizer). Īn unconfined superintelligent AI could, if its goals differed from humanity's, take actions resulting in human extinction. These improvements would make further improvements possible, which would in turn make further iterative improvements possible, and so on, leading to a sudden intelligence explosion. Some hypothetical intelligence technologies, like "seed AI", are postulated to be able to make themselves faster and more intelligent by modifying their source code. “We are not, and won't for some time.Main article: Existential risk from artificial general intelligence Some AI experts, tech entrepreneurs including Elon Musk, and scientists recently wrote an open letter calling for a six-month pause on the development of anything more powerful than GPT-4.Īt MIT last week, Altman confirmed that his company is not currently developing GPT-5. “An earlier version of the letter claimed OpenAI is training GPT-5 right now,” he said. The remarkable capabilities of GPT-4 have stunned some experts and sparked debate over the potential for AI to transform the economy but also spread disinformation and eliminate jobs. It involves having humans judge the quality of the model’s answers to steer it towards providing responses more likely to be judged as high quality. ![]() On possibility is that it used a method called reinforcement learning with human feedback, which was used to enhance ChatGPT. At the MIT event, Altman was asked if training GPT-4 cost $100 million he replied, “It’s more than that.”Īlthough OpenAI is keeping GPT-4’s size and inner workings secret, it is likely that some of its intelligence already comes from looking beyond just scale. Yet when OpenAI finally announced the new artificial intelligence model, the company didn’t disclose how big it is-perhaps because size is no longer all that matters. After ChatGPT debuted in November, meme makers and tech pundits speculated that GPT-4, when it arrived, would be a model of vertigo-inducing size and complexity.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |