Skip to content

The Q* hypothesis: Tree-of-thoughts reasoning, process reward models, and supercharging synthetic data

The Q* hypothesis: Tree-of-thoughts reasoning, process reward models, and supercharging synthetic data

Emergency special: The information we need to understand what Q* is was right in front of us, but the memes are more fun than reality.

https://www.interconnects.ai/p/q-star


The Algorithm

By Melissa Heikkilä • 11.27.23

Via “Welcome back to The Algorithm! 

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. (Only to rehire him a few days later, and replace the only two women on its board with white men. Classy!) 

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 reported 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 of 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 so 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 at the weekend that he thinks Q* is likely to be “OpenAI attempts at planning.” Read more in my story here.

Last week, I spoke live on LinkedIn with my colleagues Niall Firth and Will Douglas Heaven about OpenAI’s crazy week—and what it means for the future of AI. If you need a recap, you can catch up on what was said here. “

 

  • Pro plugin deactivated or invalid

Posted on: November 27, 2023, 10:00 am Category: Uncategorized

By: Stephen Abram

Comments Off on The Q* hypothesis: Tree-of-thoughts reasoning, process reward models, and supercharging synthetic data

0 Responses

Stay in touch with the conversation, subscribe to the RSS feed for comments on this post.