Tag: large language models
-
Technique improves the reasoning capabilities of large language models
Large language models like those that power ChatGPT have shown impressive performance on tasks like drafting legal briefs, analyzing the sentiment of customer reviews, or translating documents into different languages. These machine-learning models typically use only natural language to process information and answer queries, which can make it difficult for them to perform tasks that…
-
Researchers use large language models to help robots navigate
Someday, you may want your home robot to carry a load of dirty clothes downstairs and deposit them in the washing machine in the far-left corner of the basement. The robot will need to combine your instructions with its visual observations to determine the steps it should take to complete this task. For an AI…
-
Natural language boosts LLM performance in coding, planning, and robotics
Large language models (LLMs) are becoming increasingly useful for programming and robotics tasks, but for more complicated reasoning problems, the gap between these systems and humans looms large. Without the ability to learn new concepts like humans do, these systems fail to form good abstractions โ essentially, high-level representations of complex concepts that skip less-important…
-
Large language models use a surprisingly simple mechanism to retrieve some stored knowledge
Large language models, such as those that power popular artificial intelligence chatbots like ChatGPT, are incredibly complex. Even though these models are being used as tools in many areas, such as customer support, code generation, and language translation, scientists still donโt fully grasp how they work. In an effort to better understand what is going…
-
Engineering household robots to have a little common sense
From wiping up spills to serving up food, robots are being taught to carry out increasingly complicated household tasks. Many such home-bot trainees are learning through imitation; they are programmed to copy the motions that a human physically guides them through. It turns out that robots are excellent mimics. But unless engineers also program them…
-
A new way to let AI chatbots converse all day without crashing
When a human-AI conversation involves many rounds of continuous dialogue, the powerful large language machine-learning models that drive chatbots like ChatGPT sometimes start to collapse, causing the botsโ performance to rapidly deteriorate. A team of researchers from MIT and elsewhere has pinpointed a surprising cause of this problem and developed a simple solution that enables…
-
Multiple AI models help robots execute complex plans more transparently
Your daily to-do list is likely pretty straightforward: wash the dishes, buy groceries, and other minutiae. Itโs unlikely you wrote out โpick up the first dirty dish,โ or โwash that plate with a sponge,โ because each of these miniature steps within the chore feels intuitive. While we can routinely complete each step without much thought,…
-
AI agents help explain other AI systems
Explaining the behavior of trained neural networks remains a compelling puzzle, especially as these models grow in size and sophistication. Like other scientific challenges throughout history, reverse-engineering how artificial intelligence systems work requires a substantial amount of experimentation: making hypotheses, intervening on behavior, and even dissecting large networks to examine individual neurons. To date, most…
-
Students pitch transformative ideas in generative AI at MIT Ignite competition
This semester, students and postdocs across MIT were invited to submit ideas for the first-ever MIT Ignite: Generative AI Entrepreneurship Competition. Over 100 teams submitted proposals for startups that utilize generative artificial intelligence technologies to develop solutions across a diverse range of disciplines including human health, climate change, education, and workforce dynamics. On Oct. 30,…
-
Generating opportunities with generative AI
Talking with retail executives back in 2010, Rama Ramakrishnan came to two realizations. First, although retail systems that offered customers personalized recommendations were getting a great deal of attention, these systems often provided little payoff for retailers. Second, for many of the firms, most customers shopped only once or twice a year, so companies didn’t…