Nov 28, 2023 06:23 PM
Unpacking the hype around OpenAI’s rumored new Q* model
https://www.technologyreview.com/2023/11...w-q-model/
INTRO: Ever since last week’s dramatic events at OpenAI, the rumor mill has been in overdrive about why the company’s chief scientific officer, Ilya Sutskever, and its board decided to oust CEO Sam Altman.
While we still don’t know all the details, there have been reports that researchers at OpenAI had made a “breakthrough” in AI that had alarmed staff members. Reuters and The Information both report that researchers had come up with a new way to make powerful AI systems and had created a new model, called Q* (pronounced Q star), that was able to perform grade-school-level math. According to the people who spoke to Reuters, some at OpenAI believe this could be a milestone in the company’s quest to build artificial general intelligence, a much-hyped concept referring to an AI system that is smarter than humans. The company declined to comment on Q*.
Social media is full of speculation and excessive hype, so I called some experts to find out how big a deal any breakthrough in math and AI would really be.
Researchers have for years tried to get AI models to solve math problems. Language models like ChatGPT and GPT-4 can do some math, but not very well or reliably. We currently don’t have the algorithms or even the right architectures to be able to solve math problems reliably using AI, says Wenda Li, an AI lecturer at the University of Edinburgh. Deep learning and transformers (a kind of neural network), which is what language models use, are excellent at recognizing patterns, but that alone is likely not enough, Li adds.
Math is a benchmark for reasoning, Li says. A machine that is able to reason about mathematics, could, in theory, be able to learn to do other tasks that build on existing information, such as writing computer code or drawing conclusions from a news article. Math is a particularly hard challenge because it requires AI models to have the capacity to reason and to really understand what they are dealing with.
A generative AI system that could reliably do math would need to have a really firm grasp on concrete definitions of particular concepts that can get very abstract. A lot of math problems also require some level of planning over multiple steps, says Katie Collins, a PhD researcher at the University of Cambridge, who specializes in math and AI. Indeed, Yann LeCun, chief AI scientist at Meta, posted on X and LinkedIn over the weekend that he thinks Q* is likely to be “OpenAI attempts at planning.”
But while math capability might take us a step closer to more powerful AI systems, solving these sorts of math problems doesn’t signal the birth of a superintelligence... (MORE - details)
RELATED (scivillage): After OpenAI's blowup, it seems pretty clear that 'AI Safety' isn't a real thing ...... OpenAI drama: Biggest threat in the history of humanity?
https://www.technologyreview.com/2023/11...w-q-model/
INTRO: Ever since last week’s dramatic events at OpenAI, the rumor mill has been in overdrive about why the company’s chief scientific officer, Ilya Sutskever, and its board decided to oust CEO Sam Altman.
While we still don’t know all the details, there have been reports that researchers at OpenAI had made a “breakthrough” in AI that had alarmed staff members. Reuters and The Information both report that researchers had come up with a new way to make powerful AI systems and had created a new model, called Q* (pronounced Q star), that was able to perform grade-school-level math. According to the people who spoke to Reuters, some at OpenAI believe this could be a milestone in the company’s quest to build artificial general intelligence, a much-hyped concept referring to an AI system that is smarter than humans. The company declined to comment on Q*.
Social media is full of speculation and excessive hype, so I called some experts to find out how big a deal any breakthrough in math and AI would really be.
Researchers have for years tried to get AI models to solve math problems. Language models like ChatGPT and GPT-4 can do some math, but not very well or reliably. We currently don’t have the algorithms or even the right architectures to be able to solve math problems reliably using AI, says Wenda Li, an AI lecturer at the University of Edinburgh. Deep learning and transformers (a kind of neural network), which is what language models use, are excellent at recognizing patterns, but that alone is likely not enough, Li adds.
Math is a benchmark for reasoning, Li says. A machine that is able to reason about mathematics, could, in theory, be able to learn to do other tasks that build on existing information, such as writing computer code or drawing conclusions from a news article. Math is a particularly hard challenge because it requires AI models to have the capacity to reason and to really understand what they are dealing with.
A generative AI system that could reliably do math would need to have a really firm grasp on concrete definitions of particular concepts that can get very abstract. A lot of math problems also require some level of planning over multiple steps, says Katie Collins, a PhD researcher at the University of Cambridge, who specializes in math and AI. Indeed, Yann LeCun, chief AI scientist at Meta, posted on X and LinkedIn over the weekend that he thinks Q* is likely to be “OpenAI attempts at planning.”
But while math capability might take us a step closer to more powerful AI systems, solving these sorts of math problems doesn’t signal the birth of a superintelligence... (MORE - details)
RELATED (scivillage): After OpenAI's blowup, it seems pretty clear that 'AI Safety' isn't a real thing ...... OpenAI drama: Biggest threat in the history of humanity?