CodeSteer is a smart assistant from MIT that automatically guides large language models to switch between generating text and code, and to refine its response, until it answers a query correctly.

With the help of AI, an inexpensive test found in many doctors’ offices may soon be used to screen for hidden structural heart disease. 

About The Study: In this analytical model study, influenza vaccination provided substantial benefit in reducing infections to both the vaccinated and unvaccinated portions of the population. Even when both vaccine effectiveness and vaccine uptake were low, vaccination showed marked reductions in disease burden for transmission levels characteristic of seasonal influenza. However, when the level of transmission was very high, even a highly effective vaccine did not protect unvaccinated individuals. These findings underscore the importance of vaccination in disease prevention and control and show that indirect benefits are limited in high transmission situations. 

Until recently, there was no way for models developed by different companies to communicate directly, collaborate or combine their strengths to improve performance. This week, at the International Conference on Machine Learning (ICML) in Vancouver, Canada, scientists from the Weizmann Institute of Science and Intel Labs are presenting a new set of algorithms that overcome this barrier, enabling users to benefit from combined computational power of AI models working together. The new algorithms, already available to millions of AI developers around the world, speed up the performance of large language models (LLMs) – today’s leading models of generative AI – by 1.5 times, on average.

A new experimental design framework could enable scientists to efficiently estimate how combinations of interventions will affect a group of cells, reducing the cost of experiments and providing less biased data that could be used to understand disease mechanisms or develop new treatments.