Exposing biases, moods, personalities, and abstract concepts hidden in large language models
A new method developed at MIT could root out vulnerabilities and improve LLM safety and performance.
A new method developed at MIT could root out vulnerabilities and improve LLM safety and performance.
Just as product managers emerged during the software revolution, agent managers are becoming essential to translating strategic intent into reliable outcomes.
Read MoreEnCompass executes AI agent programs by backtracking and making multiple attempts, finding the best set of outputs generated by an LLM. It could help coders work with AI agents more efficiently.
Read MoreGetting the most out of this new technology requires revamping software, organizational structures, and workflows designed for human workers.
Read MoreAquaCulture Shock program, in collaboration with MIT-Scandinavia MISTI, offers international internships for AI and autonomy in aquaculture
Read MoreThe virtual VideoCAD tool could boost designers’ productivity and help train engineers learning computer-aided design.
Read MoreThe coding framework uses modular concepts and simple synchronization rules to make software clearer, safer, and easier for LLMs to generate.
Read MoreChemXploreML makes advanced chemical predictions easier and faster — without requiring deep programming skills.
Read MoreA team of researchers has mapped the challenges of AI in software development, and outlined a research agenda to move the field forward.
Read MoreCaitlin Morris, a PhD student and 2024 MAD Fellow affiliated with the MIT Media Lab, designs digital learning platforms that make room for the “social magic” that influences curiosity and motivation.
Read More
You must be logged in to post a comment.