British Journal of Ophthalmology

Publicly available multimodal large language models for ocular surface infections ...

Background/aims Ocular surface infections remain a major cause of visual loss worldwide, yet diagnosis often relies on slow ...

Are we overestimating AI’s abilities? New study questions how models are tested

Researchers tested AI benchmarks and found that its grading wasn’t accurate.
Unite.AI

Verbosity Decreases Accuracy in Large Language Models

New research finds that forcing Large Language Models to give shorter answers notably improves the accuracy and quality of ...

TurboQuant: Google aims to curb the memory hunger of large LLMs

Google's TurboQuant reduces the KV cache of large language models to 3 bits. Accuracy is said to remain, speed to multiply.
IEEE Spectrum on MSN

Why are large language models so terrible at video games?

AI models code simple games, but struggle to play them ...