A cost-aware evaluation compared large language models against specialized embedding models across 37 text-understanding tasks and found the best LLM…
Researchers developed Inject, Align, and Recover (IAR), a three-stage post-training framework that lets language models answer questions about specific document…
Researchers built PolicyGuide, a system that compiles organizational policies into workflow graphs and uses a proactive verifier at user-turn boundaries…
Researchers built Daedalus-150M, a 150-million-parameter language model architected specifically for efficient CPU inference rather than adapted from a GPU-designed model.…
Researchers introduced Chain-of-Experience (CoE), a test-time learning approach that allows large language models to improve iteratively using self-feedback and environmental…
Researchers introduced FlowEvo, a framework addressing the fact that workflows discovered by LLM agents during task execution are typically thrown…
Researchers ran a controlled experiment placing LLM agents on a simulated social platform to study how peer-ranked feeds shape agent…
Cognitive scientist Gary Marcus disputes Anthropic CEO Dario Amodei’s prediction that AI could cure most human disease within five to…
MIT Technology Review reports on new research finding that AI agents currently cannot conduct open-ended AI research — free-form investigation…
In his ‘Superintelligent’ newsletter column, linguist Adam Aleksic argues that the growing market of AI-text detection tools is built on…
Freelance writer Sharon Schindel, who has chronic pain and nerve damage, argues that blanket criticism of AI writing tools overlooks…
Perplexity’s promotional partnership with Indian telecom operator Airtel, which offered free 12-month Perplexity Pro subscriptions, drove 56 million downloads over…
