
General Science
Large language models are now being used as autonomous research agents that can conduct scientific studies, formulate hypotheses, run experiments, and write papers on their own. However, a critical problem has emerged: these AI-generated papers often contain errors that compound through the research process, including fake citations, misalignment between described methods and actual code, and unreproducible results. The Science One Framework is a new system designed to prevent these errors by building verifiable evidence chains throughout the research process, where every claim in a paper is linked back to its supporting evidence such as retrieved papers, experimental logs, or code. When tested against existing systems using an automated audit protocol, the Science One Framework eliminated phantom references and achieved perfect score verification while still matching or exceeding human expert performance on research tasks.

Microsoft has open sourced code-testing-generator, a polyglot agent that writes unit tests and then proves they work. It ships in the dotnet-test plugin inside the MIT-licensed dotnet/skills repository. The agent targets a gap that coding assistants usually leave open. A prompt like ‘generate unit tests’ does not say which framework, file location or assertions to use. code-testing-generator settles those decisions by reading the repository before it writes anything. It then pla

A new SaferAI report finds Z.ai's open-weight GLM-5.2 approaches frontier AI capabilities while lacking key safety mitigations, renewing concerns that powerful open models could outpace governance and safeguards.

In this tutorial, we design an end-to-end evaluation workflow for PerceptionBench. This multimodal benchmark measures fine-grained visual perception capabilities across tasks such as OCR, counting, localization, contextual reasoning, comparison, depth understanding, and hallucination detection. We begin by configuring a Colab-compatible environment, installing the required libraries, and loading a balanced subset of the dataset through a robust multi-stage streaming and download strategy. We th
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven