OpenAI, led by Sam Altman, is on the verge of revolutionizing reasoning technology for its large language models (LLMs) with a project codenamed Strawberry, as per reports from Reuters. The company is aiming to enhance the reasoning abilities of its AI models significantly with this new development.
The project, known as Strawberry, has been kept under wraps within OpenAI and was previously referred to as Q*. However, glimpses of its potential have been shown to select staff members, demonstrating LLMs’ proficiency in solving complex science and math problems that current models struggle with.
The internal documents discuss utilizing Strawberry models for empowering OpenAI’s AI not only to answer queries but also to autonomously navigate the internet for in-depth research, a concept coined as “deep research” by OpenAI.
Introducing Strawberry
Strawberry represents a unique approach to post-training AI models after their initial training on extensive datasets. It offers a specialized method to adapt and enhance OpenAI’s generative AI models for specific performance improvements even after the initial training phase.
OpenAI is looking to deploy Strawberry for tackling long-horizon tasks (LHT) that necessitate AI models to plan and execute actions over an extended period effectively. Its ultimate goal is for the models to conduct research autonomously by browsing the web using a computer using agent (CUA) to act based on their findings.
3.6 Crore Indians visited in a single day choosing us as India’s undisputed platform for General Election Results. Explore the latest updates here!
Download The Mint News App to get Daily Market Updates & Live Business News.
More
Less
Published: 13 Jul 2024, 08:25 AM IST
