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.
By minimizing the need to drive around looking for a parking spot, this technique can save drivers up to 35 minutes — and give them a realistic estimate of total travel time.
Read MoreThe context of long-term conversations can cause an LLM to begin mirroring the user’s viewpoints, possibly reducing accuracy or creating a virtual echo-chamber.
Read MoreProject AI Evidence will connect governments, tech companies, and nonprofits with world-class economists at MIT and across J-PAL’s global network to evaluate and improve AI solutions.
Read MoreAssociate Professor Rafael Gómez-Bombarelli has spent his career applying AI to improve scientific discovery. Now he believes we are at an inflection point.
Read MoreDriven by overuse and misuse of antibiotics, drug-resistant infections are on the rise, while development of new antibacterial tools has slowed.
Read MoreOpening a new window on the brainstem, a new tool reliably and finely resolves distinct nerve bundles in live diffusion MRI scans, revealing signs of injury or disease.
Read MoreMIT Sports Lab researchers are applying AI technologies to help figure skaters improve. They also have thoughts on whether five-rotation jumps are humanly possible.
Read MoreRemoving just a tiny fraction of the crowdsourced data that informs online ranking platforms can significantly change the results.
Read MoreMIT faculty join The Curiosity Desk to discuss football, math, Olympic figure skating, AI and the quest to cure ovarian cancer.
Read More
You must be logged in to post a comment.