Researchers at MIT have developed GenSQL, a new generative AI system that can be used “to ease answering data science questions,” reports Allison Proffitt for Bio-It World. “Look how much better data science could be if it was easier to use,” says Research Scientist Mathieu Huot. “It’s not perfect yet, but we believe it’s quite an improvement over other options.”
Research Scientist Mathieu Huot speaks with Tech Briefs reporter Andrew Corselli about his work with GenSQL, a generative AI system for databases that “could help users make predictions, detect anomalies, guess missing values, fix errors, or generate synthetic data with just a few keystrokes.”
Researchers at CSAIL have created three “libraries of abstraction” – a collection of abstractions within natural language that highlight the importance of everyday words in providing context and better reasoning for large language models, reports Darren Orf for Popular Mechanics. “The researchers focused on household tasks and command-based video games, and developed a language model that proposes abstractions from a dataset,” explains Orf. “When implemented with existing LLM platforms, such as GPT-4, AI actions like ‘placing chilled wine in a cabinet' or ‘craft a bed’ (in the Minecraft sense) saw a big increase in task accuracy at 59 to 89 percent, respectively.”
The Climate Modeling Alliance (CliMA), which includes a number of MIT researchers, is working on developing a new climate model that could be used to create more accurate climate predications that could be useful at the local or regional levels, reports Doug Struck for The Christian Science Monitor. “It’s always a mistake to say that you shouldn’t try something new,” says Prof. Raffaele Ferrari. “Because that’s how you change the world.”
TechRepublic reporter Nick Heath writes about Julia 1.0, a programming language created by MIT researchers. “The breadth of Julia's capabilities and ability to spread workloads across hundreds of thousands of processing cores have led to its use for everything from machine learning to large-scale supercomputer simulation,” writes Heath.
Fortune reporter Jonathan Vanian writes that researchers from MIT’s Computer Science and Artificial Intelligence Laboratory have developed a new method to restore old, malfunctioning code. The system, called Helium, “discovers the most crucial lines of code that the original programmers developed to make it function, and then builds a revised version of the program.”