We’re launching $10M in grants to support technical research towards the alignment and safety of superhuman AI systems, including weak-to-strong generalization, interpretability, scalable oversight, and more.
Superalignment Fast Grants
Related Posts
Google’s Gecko benchmark identifies best AI image generator
Google’s DeepMind released Gecko, a new benchmark for comprehensively evaluating AI text-to-image (T2I) models. Over the last two years, we’ve seen AI image generators like DALL-E and Midjourney become progressively better with each version release. However, deciding which of the underlying models these platforms use is best has been largely subjective and difficult to benchmark. To make a broad claim that one model is “better” than another isn’t so simple. Different models excel in various aspects of image generation. One may be good at text rendering while another may be better at object interaction. A key challenge that T2I models
The post Google’s Gecko benchmark identifies best AI image generator appeared first on DailyAI.
- Algorithms
- Artificial intelligence
- Computer science and technology
- Computer vision
- Data
- Defense Advanced Research Projects Agency (DARPA)
- Electrical Engineering & Computer Science (eecs)
- Machine learning
- MIT Schwarzman College of Computing
- MIT-IBM Watson AI Lab
- National Science Foundation (NSF)
- Research
- Robotics
- School of Engineering
Multiple AI models help robots execute complex plans more transparently
A multimodal system uses models trained on language, vision, and action data to help robots develop and execute plans for household, construction, and manufacturing tasks.
Doctors have more difficulty diagnosing disease when looking at images of darker skin
Dermatologists and general practitioners are somewhat less accurate in diagnosing disease in darker skin, a new study finds. Used correctly, AI may be able to help.