OpenAI’s latest product lets you vibe code science
OpenAI's Prism: Revolutionizing Scientific Research with AI-Powered Writing
OpenAI, the company behind the popular language model ChatGPT, has been making waves in the scientific community with its latest product, Prism. This free tool embeds ChatGPT in a text editor, allowing scientists to write scientific papers with the help of AI. The idea is to put ChatGPT front and center inside software that scientists use to write up their work, much like chatbots are now embedded into popular programming editors. This is often referred to as "vibe coding," but for science.
The Need for AI in Science
According to Kevin Weil, head of OpenAI for Science, around 1.3 million scientists around the world submit more than 8 million queries a week to ChatGPT on advanced topics in science and math. This tells us that AI is moving from curiosity to core workflow for scientists. Weil believes that AI will have a significant impact on science, not just in making new discoveries, but also in accelerating existing research.
How Prism Works
Prism incorporates GPT-5.2, OpenAI's best model yet for mathematical and scientific problem-solving, into an editor for writing documents in LaTeX, a common coding language that scientists use for formatting scientific papers. A ChatGPT chat box sits at the bottom of the screen, below a view of the article being written. Scientists can call on ChatGPT for anything they want, from drafting text to summarizing related articles, managing citations, turning photos of whiteboard scribbles into equations or diagrams, or talking through hypotheses or mathematical proofs.
The Benefits of Prism
Prism could be a huge time saver for scientists. It can help them focus on the creative aspects of research, rather than getting bogged down in tedious tasks like formatting and citation management. Nikita Zhivotovskiy, a statistician at the University of California, Berkeley, says GPT-5 has already become an important tool in his work. "It sometimes helps polish the text of papers, catching mathematical typos or bugs, and provides generally useful feedback," he says.
Addressing Concerns about AI in Science
Some scientists may be concerned that AI will replace human researchers or make it easier for them to produce low-quality research. However, Weil argues that AI will not replace human researchers, but rather augment their abilities. "I think more powerfully—and with 100% probability—there’s going to be 10,000 advances in science that maybe wouldn’t have happened or wouldn't have happened as quickly, and AI will have been a contributor to that," he says.
The Future of AI in Science
Weil believes that AI will have a significant impact on science in the coming years, not just in making new discoveries, but also in accelerating existing research. He predicts that AI will become an integral part of the scientific process, helping researchers to analyze data, identify patterns, and make new connections. This will lead to a new era of scientific discovery, where AI and human researchers work together to push the boundaries of human knowledge.
Conclusion
OpenAI's Prism is a significant development in the field of AI and science. It has the potential to revolutionize the way scientists write and publish research papers, making it easier and faster for them to share their findings with the world. While there may be concerns about the impact of AI on human researchers, Weil believes that AI will augment their abilities, rather than replace them. As AI continues to evolve and improve, we can expect to see even more exciting developments in the field of science.
Deep Dive
- Artificial Intelligence: The great AI hype correction of 2025
- Meet the new biologists treating LLMs like aliens: By studying large language models as if they were living things instead of computer programs, scientists are discovering some of their secrets for the first time.
- What’s next for AI in 2026: Our AI writers make their big bets for the coming year—here are five hot trends to watch.
- Yann LeCun’s new venture is a contrarian bet against large language models: In an exclusive interview, the AI pioneer shares his plans for his new Paris-based company, AMI Labs.
Stay connected
- Get the latest updates from MIT Technology Review: Discover special offers, top stories, upcoming events, and more.
- Enter your email: Privacy Policy
- Explore more newsletters: It looks like something went wrong. We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at [email protected] with a list of newsletters you’d like to receive.
